awesome-ocr
papers about ocr
https://github.com/ChanChiChoi/awesome-ocr
Last synced: 23 days ago
JSON representation
-
Uncategorized
-
Uncategorized
- 1
- 2
- 3
- Handwritten Script Identification from Text Lines
- Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks
- Text Prior Guided Scene Text Image Super-resolution
- Scene Text Visual Question Answering
- TedEval: A Fair Evaluation Metric for Scene Text Detectors
- Deep Neural Network for Semantic-based Text Recognition in Images
- Geometry Normalization Networks for Accurate Scene Text Detection
- ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
- 4
- 5
- 6
- 7
- 9
- Character recognition in natural images
- Detecting text in natural scenes with stroke width transform - 2970.<br>
- Browsing heterogeneous document collections by a segmentation-free word spotting method - 67.
- Text localization in real-world images using efficiently pruned exhaustive search - 691.
- End-to-end text recognition with convolutional neural networks - 3308.<br>
- Text recognition in videos using a recurrent connectionist approach - 179.
- A novel word spotting method based on recurrent neural networks - 224.
- Real-time scene text localization and recognition - 3545.<br>
- Top-down and bottom-up cues for scene text recognition - 2694.
- Robust text detection in natural scene images - 983.
- Photoocr: Reading text in uncontrolled conditions - 792.
- High-performance OCR for printed English and Fraktur using LSTM networks - 687.<br>
- Image binarization for end-to-end text understanding in natural images - 132.
- Scene text recognition using part-based tree-structured character detection - 2968.
- Arabic text recognition in video sequences
- Text Recognition in both ancient and cartographic documents
- End-to-end text recognition with hybrid HMM maxout models
- Curriculum learning for handwritten text line recognition - 60.
- Multi-digit number recognition from street view imagery using deep convolutional neural networks
- Efficient character skew rectification in scene text images - 146.
- Word spotting and recognition with embedded attributes - 2566.<br>
- A comparison of sequence-trained deep neural networks and recurrent neural networks optical modeling for handwriting recognition - 210.
- A unified framework for multioriented text detection and recognition - 4749.
- Renet: A recurrent neural network based alternative to convolutional networks
- Robust scene text detection with convolution neural network induced mser trees - 511.
- Bangla text recognition from video sequence: A new focus
- Synthetic data and artificial neural networks for natural scene text recognition
- Reading text in the wild with convolutional neural networks - 20.<br>
- Deep structured output learning for unconstrained text recognition
- Deepfont: Identify your font from an image - 459.
- Object proposals for text extraction in the wild - 210.[[code]( https://github.com/lluisgomez/TextProposals)]
- Automatic script identification in the wild - 535.
- Fastext: Efficient unconstrained scene text detector - 1214.[[code](https://github.com/MichalBusta/FASText)]
- A hypothesize-and-verify framework for text recognition using deep recurrent neural networks - 940.
- Efficient scene text localization and recognition with local character refinement - 750.
- High performance offline handwritten chinese character recognition using googlenet and directional feature maps - 850.<br>
- An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition - 2304.<br>
- Text-attentional convolutional neural network for scene text detection - 2541.
- Sequence to sequence learning for optical character recognition
- Similarity-based Text Recognition by Deeply Supervised Siamese Network
- Robust Scene Text Recognition Using Sparse Coding based Features
- Scene text detection and recognition: Recent advances and future trends - 36.
- Reading Scene Text in Deep Convolutional Sequences - 3508.<br>
- Recursive recurrent nets with attention modeling for OCR in the wild - 2239.
- I am robot:(deep) learning to break semantic image captchas - 403.
- Real-time lexicon-free scene text localization and recognition - 1885.
- Multi-oriented text detection with fully convolutional networks - 4167.
- TextCatcher: a method to detect curved and challenging text in natural scenes - 117.
- Canny text detector: Fast and robust scene text localization algorithm - 3573.
- Memory Matters: Convolutional Recurrent Neural Network for Scene Text Recognition
- Enhancing energy minimization framework for scene text recognition with top-down cues - 42.
- Reading car license plates using deep convolutional neural networks and lstms
- Coco-text: Dataset and benchmark for text detection and recognition in natural images
- Context modeling for semantic text matching and scene text detection
- Scene Text Detection in Video by Learning Locally and Globally - 2653.
- Robust scene text recognition with automatic rectification - 4176.
- Character Proposal Network for Robust Text Extraction
- A fine-grained approach to scene text script identification
- Improving patch-based scene text script identification with ensembles of conjoined networks
- Accurate text localization in natural image with cascaded convolutional text network
- Writer-independent feature learning for offline signature verification using deep convolutional neural networks - 2583.
- A CNN Based Scene Chinese Text Recognition Algorithm With Synthetic Data Engine
- A Novel Scene Text Detection Algorithm Based On Convolutional Neural Network
- Textproposals: a text-specific selective search algorithm for word spotting in the wild - 74.[[code](https://github.com/lluisgomez/TextProposals)]
- Scan, attend and read: End-to-end handwritten paragraph recognition with mdlstm attention
- Multi-Oriented Text Detection with Fully Convolutional Networks
- Fully convolutional recurrent network for handwritten Chinese text recognition - 4016.
- Text Flow: A Unified Text Detection System in Natural Scene Images
- Deeptext: A unified framework for text proposal generation and text detection in natural images
- Drawing and recognizing chinese characters with recurrent neural network
- Scene text detection via holistic, multi-channel prediction
- Sequence to sequence learning for unconstrained scene text recognition
- Automatic text extraction and character segmentation using maximally stable extremal regions
- Generating Synthetic Data for Text Recognition
- Detecting text in natural image with connectionist text proposal network - 72.<br>
- Learning spatial-semantic context with fully convolutional recurrent network for online handwritten chinese text recognition
- Stroke Sequence-Dependent Deep Convolutional Neural Network for Online Handwritten Chinese Character Recognition
- An Image Dataset of Text Patches in Everyday Scenes
- Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data - 2801.
- End-to-End Subtitle Detection and Recognition for Videos in East Asian Languages via CNN Ensemble with Near-Human-Level Performance
- A DNN Framework For Text Image Rectification From Planar Transformations
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network
- Statistical Learning for OCR Text Correction
- Smart Library: Identifying Books in a Library using Richly Supervised Deep Scene Text Reading
- Usability Investigation on the Localization of Text CAPTCHAs: Take Chinese Characters as a Case Study
- Recognition of Text Image Using Multilayer Perceptron
- A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing
- Profiling of OCR'ed Historical Texts Revisited
- Segmentation-free Vehicle License Plate Recognition using ConvNet-RNN
- Printed Arabic Text Recognition using Linear and Nonlinear Regression
- End-to-end interpretation of the french street name signs dataset - 426.<br>
- Improving Text Proposals for Scene Images with Fully Convolutional Networks
- Using Synthetic Data to Train Neural Networks is Model-Based Reasoning
- Arbitrary-Oriented Scene Text Detection via Rotation Proposals
- Deep matching prior network: Toward tighter multi-oriented text detection
- Detecting Oriented Text in Natural Images by Linking Segments
- License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network - 4167.<br>
- Deep Direct Regression for Multi-Oriented Scene Text Detection
- Cascaded Segmentation-Detection Networks for Word-Level Text Spotting
- EAST: An Efficient and Accurate Scene Text Detector
- Attention-based Extraction of Structured Information from Street View Imagery
- Full-Page Text Recognition: Learning Where to Start and When to Stop
- Scene Text Eraser
- Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling
- WordFence: Text Detection in Natural Images with Border Awareness
- Visual attention models for scene text recognition
- Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis
- Text Extraction From Texture Images Using Masked Signal Decomposition
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
- R-PHOC: Segmentation-Free Word Spotting using CNN
- Adversarial generation of training examples for vehicle license plate recognition
- Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
- Multi-Oriented Text Detection and Verification in Video Frames and Scene Images
- Text recognition in scene image and video frame using Color Channel selection - 28.
- Date-Field Retrieval in Scene Image and Video Frames using Text Enhancement and Shape Coding
- STN-OCR: A single Neural Network for Text Detection and Text Recognition
- Deep Scene Text Detection with Connected Component Proposals
- Spotting Separator Points at Line Terminals in Compressed Document Images for Text-line Segmentation
- Color and Gradient Features for Text Segmentation from Video Frames
- Wordsup: Exploiting word annotations for character based text detection
- Single shot text detector with regional attention
- Scene Text Recognition with Sliding Convolutional Character Models
- On-the-fly Historical Handwritten Text Annotation
- Focusing Attention: Towards Accurate Text Recognition in Natural Images - 5094.
- Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
- Exploring Geometric Property Thresholds For Filtering Non-Text Regions In A Connected Component Based Text Detection Application
- Reading Scene Text with Attention Convolutional Sequence Modeling
- Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks
- Real time text localization for Indoor Mobile Robot Navigation
- Handwritten digit string recognition by combination of residual network and RNN-CTC - 591.
- AdaDNNs: Adaptive Ensemble of Deep Neural Networks for Scene Text Recognition
- WeText: Scene Text Detection under Weak Supervision
- Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition
- Unconstrained scene text and video text recognition for Arabic script - 30.
- A New Hybrid-parameter Recurrent Neural Networks for Online Handwritten Chinese Character Recognition
- Deep Residual Text Detection Network for Scene Text
- Arbitrarily-Oriented Text Recognition
- Feature Enhancement Network: A Refined Scene Text Detector
- ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
- Detecting Curve Text in the Wild: New Dataset and New Solution
- Attention networks for image-to-text
- Enhanced Characterness for Text Detection in the Wild
- SEE: Towards Semi-Supervised End-to-End Scene Text Recognition
- Detection and Recognition of Text Embedded in Online Images via Neural Context Models - 4110.<br>
- PixelLink: Detecting Scene Text via Instance Segmentation
- Text Extraction and Retrieval from Smartphone Screenshots: Building a Repository for Life in Media
- FOTS: Fast Oriented Text Spotting with a Unified Network
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- TexT - Text Extractor Tool for Handwritten Document Transcription and Annotation
- E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text
- Sliding Line Point Regression for Shape Robust Scene Text Detection
- A Two-Stage Method for Text Line Detection in Historical Documents
- Fooling OCR Systems with Adversarial Text Images
- Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
- Chinese Text in the Wild
- Rotation-Sensitive Regression for Oriented Scene Text Detection
- Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-end Model
- Text Detection and Recognition in images: A survey
- Boosting Handwriting Text Recognition in Small Databases with Transfer Learning
- Detecting Multi-Oriented Text with Corner-based Region Proposals
- Synthetic data generation for Indic handwritten text recognition
- Guided Attention for Large Scale Scene Text Verification
- An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
- IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
- A probabilistic framework for handwritten text line segmentation
- Edit Probability for Scene Text Recognition
- Boosting up Scene Text Detectors with Guided CNN
- Learning Markov Clustering Networks for Scene Text Detection
- SCAN: Sliding Convolutional Attention Network for Scene Text Recognition
- NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition
- Shape Robust Text Detection with Progressive Scale Expansion Network
- Offline Extraction of Indic Regional Language from Natural Scene Image using Text Segmentation and Deep Convolutional Sequence
- Don't only Feel Read: Using Scene text to understand advertisements
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
- A Single Shot Text Detector with Scale-adaptive Anchors
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
- Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
- Adaptive Adversarial Attack on Scene Text Recognition
- Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
- An Efficient End-to-End Neural Model for Handwritten Text Recognition
- Double Supervised Network with Attention Mechanism for Scene Text Recognition
- Parsimonious HMMs for Offline Handwritten Chinese Text Recognition
- Single Shot Scene Text Retrieval
- TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade
- Parametric Synthesis of Text on Stylized Backgrounds using PGGANs
- Cursive Scene Text Analysis by Deep Convolutional Linear Pyramids
- Correlation Propagation Networks for Scene Text Detection
- Visual Semantic Re-ranker for Text Spotting
- Visual Re-ranking with Natural Language Understanding for Text Spotting
- Scene Text Detection and Recognition: The Deep Learning Era
- Improving Rotated Text Detection with Rotation Region Proposal Networks
- Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
- A Novel Integrated Framework for Learning both Text Detection and Recognition
- Mask R-CNN with Pyramid Attention Network for Scene Text Detection
- A pooling based scene text proposal technique for scene text reading in the wild
- Deep Laplacian Pyramid Network for Text Images Super-Resolution
- TextMountain: Accurate Scene Text Detection via Instance Segmentation
- Auto-Encoder-BoF/HMM System for Arabic Text Recognition
- Advances of Scene Text Datasets
- Simultaneous Recognition of Horizontal and Vertical Text in Natural Images
- Recurrent Calibration Network for Irregular Text Recognition
- Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition
- TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
- Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
- Detecting Text in the Wild with Deep Character Embedding Network
- MSR: Multi-Scale Shape Regression for Scene Text Detection
- SAFE: Scale Aware Feature Encoder for Scene Text Recognition
- Generating Text Sequence Images for Recognition
- Scene Text Synthesis for Efficient and Effective Deep Network Training
- Text line Segmentation in Compressed Representation of Handwritten Document using Tunneling Algorithm
- Adversarial Generation of Handwritten Text Images Conditioned on Sequences
- STEFANN: Scene Text Editor using Font Adaptive Neural Network
- Efficient Video Scene Text Spotting: Unifying Detection, Tracking, and Recognition
- Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition
- Curve Text Detection with Local Segmentation Network and Curve Connection
- ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
- Pyramid Mask Text Detector
- CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor
- COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation
- A Simple and Robust Convolutional-Attention Network for Irregular Text Recognition
- TextCaps : Handwritten Character Recognition with Very Small Datasets
- A Scalable Handwritten Text Recognition System
- FACLSTM: ConvLSTM with Focused Attention for Scene Text Recognition
- TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text
- TextCohesion: Detecting Text for Arbitrary Shapes
- Controllable Artistic Text Style Transfer via Shape-Matching GAN
- TE141K: Artistic Text Benchmark for Text Effects Transfer
- Predictive Ensemble Learning with Application to Scene Text Detection
- Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding
- Scene Text Visual Question Answering
- Selective Style Transfer for Text
- Towards Document Image Quality Assessment: A Text Line Based Framework and A Synthetic Text Line Image Dataset
- Omnidirectional Scene Text Detection with Sequential-free Box Discretization
- Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network
- 2D Attentional Irregular Scene Text Recognizer
- Towards End-to-End Text Spotting in Natural Scenes
- Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts
- ICDAR 2019 Competition on Scene Text Visual Question Answering
- Scene Text Magnifier
- ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
- TedEval: A Fair Evaluation Metric for Scene Text Detectors
- Semi-Bagging Based Deep Neural Architecture to Extract Text from High Entropy Images
- RFBTD: RFB Text Detector
- SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
- GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
- 2D-CTC for Scene Text Recognition
- Generative Adversarial Network for Handwritten Text
- It's All About The Scale -- Efficient Text Detection Using Adaptive Scaling
- Automatic Text Line Segmentation Directly in JPEG Compressed Document Images
- Towards Pure End-to-End Learning for Recognizing Multiple Text Sequences from an Image
- Deep Neural Network for Semantic-based Text Recognition in Images
- Editing Text in the Wild
- Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
- An End-to-end Video Text Detector with Online Tracking
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
- FaSTExt: Fast and Small Text Extractor
- Adaptive Embedding Gate for Attention-Based Scene Text Recognition
- End-To-End Measure for Text Recognition
- Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
- Focus-Enhanced Scene Text Recognition with Deformable Convolutions
- Alchemy: Techniques for Rectification Based Irregular Scene Text Recognition
- Geometry Normalization Networks for Accurate Scene Text Detection
- ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
- STELA: A Real-Time Scene Text Detector with Learned Anchor
- Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
- EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
- MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
- Next integrated result modelling for stopping the text field recognition process in a video using a result model with per-character alternatives
- On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
- Rosetta: Large scale system for text detection and recognition in images
- Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks
- OmniTrack: Real-time detection and tracking of objects, text and logos in video
- DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images
- Scene Text Recognition with Temporal Convolutional Encoder
- Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory
- SA-Text: Simple but Accurate Detector for Text of Arbitrary Shapes
- Learning to Predict More Accurate Text Instances for Scene Text Detection
- Real-time Scene Text Detection with Differentiable Binarization
- Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
- Methods of Weighted Combination for Text Field Recognition in a Video Stream
- Patch Aggregator for Scene Text Script Identification
- A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
- TextSLAM: Visual SLAM with Planar Text Features
- Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
- Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks
- MTRNet++: One-stage Mask-based Scene Text Eraser
- Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition
- TextTubes for Detecting Curved Text in the Wild
- Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection
- ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
- TreyNet: A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages
- Decoupled Attention Network for Text Recognition
- TextScanner: Reading Characters in Order for Robust Scene Text Recognition
- A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection
- Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
- Text Extraction and Restoration of Old Handwritten Documents
- Fast Dense Residual Network: Enhancing Global Dense Feature Flow for Text Recognition
- Scene Text Recognition With Finer Grid Rectification
- GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition
- A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling
- Scale-Invariant Multi-Oriented Text Detection in Wild Scene Images
- Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
- DGST : Discriminator Guided Scene Text detector
- Efficient Backbone Search for Scene Text Recognition
- Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
- ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
- Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
- Scene Text Recognition via Transformer
- SwapText: Image Based Texts Transfer in Scenes
- Unsupervised text line segmentation
- ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation
- UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
- Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
- ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition
- ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
- Image Processing Based Scene-Text Detection and Recognition with Tesseract
- All you need is a second look: Towards Tighter Arbitrary shape text detection
- On Vocabulary Reliance in Scene Text Recognition
- Large Scale Font Independent Urdu Text Recognition System
- RoadText-1K: Text Detection & Recognition Dataset for Driving Videos
- SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
- Self-Training for Domain Adaptive Scene Text Detection
- NENET: An Edge Learnable Network for Link Prediction in Scene Text
- Learning Robust Feature Representations for Scene Text Detection
- A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video
- Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition
- TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
- Realistic text replacement with non-uniform style conditioning
- Text Detection and Recognition in the Wild: A Review
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
- OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
- Lyric Video Analysis Using Text Detection and Tracking
- Text Detection on Roughly Placed Books by Leveraging a Learning-based Model Trained with Another Domain Data
- Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models
- Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval
- Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents
- Text Recognition -- Real World Data and Where to Find Them
- Maximum Entropy Regularization and Chinese Text Recognition
- FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection
- Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
- Character Region Attention For Text Spotting
- AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
- Fast Approximate Modelling of the Next Combination Result for Stopping the Text Recognition in a Video
- TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
- Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text
- EASTER: Efficient and Scalable Text Recognizer
- Scene Text Detection with Selected Anchor
- Visual Attack and Defense on Text
- Complicating the Social Networks for Better Storytelling: An Empirical Study of Chinese Historical Text and Novel
- An End-to-End Attack on Text-based CAPTCHAs Based on Cycle-Consistent Generative Adversarial Network
- Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
- Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild
- A Hybrid Deep Learning Model for Arabic Text Recognition
- Text-independent writer identification using convolutional neural network
- Adaptive Text Recognition through Visual Matching
- Handwritten Script Identification from Text Lines
- Exploring Font-independent Features for Scene Text Recognition
- Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval
- Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition
- Unconstrained Text Detection in Manga
- A Human Eye-based Text Color Scheme Generation Method for Image Synthesis
- Gaussian Constrained Attention Network for Scene Text Recognition
- TLGAN: document Text Localization using Generative Adversarial Nets
- Real-Time Text Detection and Recognition
- On-Device Language Identification of Text in Images using Diacritic Characters
- OCR Post Correction for Endangered Language Texts
- Digging Deeper into CRNN Model in Chinese Text Images Recognition
- Scene text removal via cascaded text stroke detection and erasing
- Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering
- SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training
- Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm
- Boosting offline handwritten text recognition in historical documents with few labeled lines
- End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network
- StacMR: Scene-Text Aware Cross-Modal Retrieval
- Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?
- Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network
- Scene Text Detection with Scribble Lines
- Research on All-content Text Recognition Method for Financial Ticket Image
- Political Posters Identification with Appearance-Text Fusion
- On Calibration of Scene-Text Recognition Models
- Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
- Enhancing Handwritten Text Recognition with N-gram sequence decomposition and Multitask Learning
- Scene Text Detection for Augmented Reality -- Character Bigram Approach to reduce False Positive Rate
- Research on Fast Text Recognition Method for Financial Ticket Image
- Robust Text CAPTCHAs Using Adversarial Examples
- Text line extraction using fully convolutional network and energy minimization
- VML-MOC: Segmenting a multiply oriented and curved handwritten text lines dataset
- Text Line Segmentation for Challenging Handwritten Document Images Using Fully Convolutional Network
- HANA: A HAndwritten NAme Database for Offline Handwritten Text Recognition
- Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models
- CSTR: A Classification Perspective on Scene Text Recognition
- Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links
- What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
- Urdu Handwritten Text Recognition Using ResNet18
- TS-Net: OCR Trained to Switch Between Text Transcription Styles
- Tracking Based Semi-Automatic Annotation for Scene Text Videos
- Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo
- MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
- Scene Text Retrieval via Joint Text Detection and Similarity Learning
- MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
- 1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit
- Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam
- RayNet: Real-time Scene Arbitrary-shape Text Detection with Multiple Rays
- PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
- Rethinking Text Line Recognition Models
- TeLCoS: OnDevice Text Localization with Clustering of Script
- Line Segmentation from Unconstrained Handwritten Text Images using Adaptive Approach
- Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
- Stroke-Based Scene Text Erasing Using Synthetic Data for Training
- PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
- ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
- TextAdaIN: Fine-Grained AdaIN for Robust Text Recognition
- Primitive Representation Learning for Scene Text Recognition
- An end-to-end Optical Character Recognition approach for ultra-low-resolution printed text images
- MT: Multi-Perspective Feature Learning Network for Scene Text Detection
- TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text
- I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition
- Unsupervised learning of text line segmentation by differentiating coarse patterns
- LineCounter: Learning Handwritten Text Line Segmentation by Counting
- DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents
- Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter
- Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition
- TextStyleBrush: Transfer of Text Aesthetics from a Single Example
- Open Images V5 Text Annotation and Yet Another Mask Text Spotter
- All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection
- A Simple and Strong Baseline: Progressively Region-based Scene Text Removal Networks
- Recurrent neural network transducer for Japanese and Chinese offline handwritten text recognition
- E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles
- Contrastive Graph Multimodal Model for Text Classification in Videos
- Transformer based Urdu Handwritten Text Optical Character Reader
- BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line Segmentation
- TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask
- Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition
- BusiNet -- a Light and Fast Text Detection Network for Business Documents
- Explore Faster Localization Learning For Scene Text Detection
- Detection of Furigana Text in Images
- Towards Multimodal Vision-Language Models Generating Non-Generic Text
- A Lexicon and Depth-wise Separable Convolution Based Handwritten Text Recognition System
- COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
- Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
- Scene Text Recognition with Permuted Autoregressive Sequence Models
- Decoupling Recognition from Detection: Single Shot Self-Reliant Scene Text Spotter
- 2D Self-Organized ONN Model For Handwritten Text Recognition
- Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
- SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition
- Progressive Scene Text Erasing with Self-Supervision
- Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning
- Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach
- Runner-Up Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: Cropped Word Recognition
- PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition
- Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition
- GLASS: Global to Local Attention for Scene-Text Spotting
- The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition
- Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions
- Shift Variance in Scene Text Detection
- DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection
- To show or not to show: Redacting sensitive text from videos of electronic displays
- Arbitrary Shape Text Detection via Segmentation with Probability Maps
- ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
- Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
- TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
- TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text
- Kernel Proposal Network for Arbitrary Shape Text Detection
- Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel
- ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment
- CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
- Bidirectional Regression for Arbitrary-Shaped Text Detection
- SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
- RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image
- Comprehensive Studies for Arbitrary-shape Scene Text Detection
- ICDAR 2021 Competition on Scene Video Text Spotting
- Towards the Unseen: Iterative Text Recognition by Distilling from Errors
- Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
- Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition
- Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection
- Why You Should Try the Real Data for the Scene Text Recognition
- I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection
- IFR: Iterative Fusion Based Recognizer For Low Quality Scene Text Recognition
- MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
- Text-Aware Single Image Specular Highlight Removal
- Data Augmentation for Scene Text Recognition
- Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling
- From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
- StackMix and Blot Augmentations for Handwritten Text Recognition
- Scene Text recognition with Full Normalization
- STRIVE: Scene Text Replacement In Videos
- Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images
- PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
- Urdu text in natural scene images: a new dataset and preliminary text detection
- De-rendering Stylized Texts
- KOHTD: Kazakh Offline Handwritten Text Dataset
- On Exploring and Improving Robustness of Scene Text Detection Models
- Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes
- Towards Open-Set Text Recognition via Label-to-Prototype Learning
- Real-time Scene Text Detection Based on Global Level and Word Level Features
- ARTS: Eliminating Inconsistency between Text Detection and Recognition with Auto-Rectification Text Spotter
- Industrial Scene Text Detection with Refined Feature-attentive Network
- TPSNet: Thin-Plate-Spline Representation for Arbitrary Shape Scene Text Detection
- FAST: Searching for a Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
- Improving Structured Text Recognition with Regular Expression Biasing
- TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance
- Adaptive Shrink-Mask for Text Detection
- Exploiting Multi-Scale Fusion, Spatial Attention and Patch Interaction Techniques for Text-Independent Writer Identification
- CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
- Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages
- Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition
- Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
- Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection
- Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
- Natural Scene Text Editing Based on AI
- On-Device Spatial Attention based Sequence Learning Approach for Scene Text Script Identification
- Visual-Semantic Transformer for Scene Text Recognition
- A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
- Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection
- Handwritten text generation and strikethrough characters augmentation
- CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning
- SPTS: Single-Point Text Spotting
- Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
- StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation
- Contrastive Learning of Semantic and Visual Representations for Text Tracking
- Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
- SAFL: A Self-Attention Scene Text Recognizer with Focal Loss
- Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence
- Transfer Learning for Scene Text Recognition in Indian Languages
- Towards Boosting the Accuracy of Non-Latin Scene Text Recognition
- Weakly Supervised Scene Text Detection using Deep Reinforcement Learning
- Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning
- AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks
- Importance of Textlines in Historical Document Classification
- Self-paced learning to improve text row detection in historical documents with missing labels
- Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer
- Offline Text-Independent Writer Identification based on word level data
- Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
- Arbitrary Shape Text Detection using Transformers
- SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text
- A Glyph-driven Topology Enhancement Network for Scene Text Recognition
- Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting
- Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
- DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting
- Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching
- APRNet: Attention-based Pixel-wise Rendering Network for Photo-Realistic Text Image Generation
- A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution
- SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
- SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization
- End-to-End Video Text Spotting with Transformer
- Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition
- Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods
- Knowledge Mining with Scene Text for Fine-Grained Recognition
- Towards End-to-End Unified Scene Text Detection and Layout Analysis
- Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
- ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
- Text Spotting Transformers
- IterVM: Iterative Vision Modeling Module for Scene Text Recognition
- Aesthetic Text Logo Synthesis via Content-aware Layout Inferring
- Content and Style Aware Generation of Text-line Images for Handwriting Recognition
- Pushing the Performance Limit of Scene Text Recognizer without Human Annotation
- Vision-Language Pre-Training for Boosting Scene Text Detectors
- SVTR: Scene Text Recognition with a Single Visual Model
- Text Detection on Technical Drawings for the Digitization of Brown-field Processes
- Multimodal Semi-Supervised Learning for Text Recognition
- UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection
- Arbitrary Shape Text Detection via Boundary Transformer
- TextMatcher: Cross-Attentional Neural Network to Compare Image and Text
- Text Detection & Recognition in the Wild for Robot Localization
- LexiconNet: An End-to-End Handwritten Paragraph Text Recognition System
- Easter2.0: Improving convolutional models for handwritten text recognition
- MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining
- CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor
- TextCohesion: Detecting Text for Arbitrary Shapes
- DGST : Discriminator Guided Scene Text detector
- SwapText: Image Based Texts Transfer in Scenes
- Location-Aware Feature Selection for Scene Text Detection
- Tightness-aware Evaluation Protocol for Scene Text Detection
- TE141K: Artistic Text Benchmark for Text Effects Transfer
- Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
- All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
- Scene Text Image Super-Resolution in the Wild
- Text line extraction using fully convolutional network and energy minimization
- VML-MOC: Segmenting a multiply oriented and curved handwritten text lines dataset
- ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
- Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
- Towards Open-Set Text Recognition via Label-to-Prototype Learning
- E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles
- Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
- Arbitrary Shape Text Detection via Segmentation with Probability Maps
- Fast Dense Residual Network: Enhancing Global Dense Feature Flow for Text Recognition
- A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video
- RFBTD: RFB Text Detector
- Character Region Awareness for Text Detection
- ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
- Text Detection on Technical Drawings for the Digitization of Brown-field Processes
- Character recognition in natural images
- Controllable Artistic Text Style Transfer via Shape-Matching GAN
- Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation
- Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection
- Real-time Scene Text Detection Based on Global Level and Word Level Features
- FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition
- Recurrent neural network transducer for Japanese and Chinese offline handwritten text recognition
- A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection
- Advances of Scene Text Datasets
- Unsupervised text line segmentation
- Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling
- SPTS: Single-Point Text Spotting
- Content and Style Aware Generation of Text-line Images for Handwriting Recognition
- OCR Post Correction for Endangered Language Texts
- RRPN++: Guidance Towards More Accurate Scene Text Detection
- What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
- Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
- Fourier Contour Embedding for Arbitrary-Shaped Text Detection
- KOHTD: Kazakh Offline Handwritten Text Dataset
- SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text
- EnsNet: Ensconce Text in the Wild
- TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade
- Scene Text Recognition from Two-Dimensional Perspective
- Parametric Synthesis of Text on Stylized Backgrounds using PGGANs
- Cursive Scene Text Analysis by Deep Convolutional Linear Pyramids
- Correlation Propagation Networks for Scene Text Detection
- Visual Semantic Re-ranker for Text Spotting
- Visual Re-ranking with Natural Language Understanding for Text Spotting
- Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition
- Improving Rotated Text Detection with Rotation Region Proposal Networks
- Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
- A Novel Integrated Framework for Learning both Text Detection and Recognition
- Mask R-CNN with Pyramid Attention Network for Scene Text Detection
- A pooling based scene text proposal technique for scene text reading in the wild
- Deep Laplacian Pyramid Network for Text Images Super-Resolution
- TextMountain: Accurate Scene Text Detection via Instance Segmentation
- Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text
- Arbitrary Shape Text Detection via Boundary Transformer
- Auto-Encoder-BoF/HMM System for Arabic Text Recognition
- ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification
- TET-GAN: Text Effects Transfer via Stylization and Destylization
- Simultaneous Recognition of Horizontal and Vertical Text in Natural Images
- Recurrent Calibration Network for Irregular Text Recognition
- Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition
- Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
- Detecting Text in the Wild with Deep Character Embedding Network
- TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
- MSR: Multi-Scale Shape Regression for Scene Text Detection
- A Multi-Object Rectified Attention Network for Scene Text Recognition - Luo/MORAN_v2](https://github.com/Canjie-Luo/MORAN_v2)]
- SAFE: Scale Aware Feature Encoder for Scene Text Recognition
- Generating Text Sequence Images for Recognition
- Scene Text Synthesis for Efficient and Effective Deep Network Training
- Text line Segmentation in Compressed Representation of Handwritten Document using Tunneling Algorithm
- Adversarial Generation of Handwritten Text Images Conditioned on Sequences
- STEFANN: Scene Text Editor using Font Adaptive Neural Network
- Efficient Video Scene Text Spotting: Unifying Detection, Tracking, and Recognition
- A Simple and Robust Convolutional-Attention Network for Irregular Text Recognition
- What is wrong with scene text recognition model comparisons? dataset and model analysis
- Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
- Manifold Mixup improves text recognition with CTC loss
- Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition
- Towards Robust Curve Text Detection with Conditional Spatial Expansion
- Curve Text Detection with Local Segmentation Network and Curve Connection
- ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
- Pyramid Mask Text Detector
- Shape Robust Text Detection with Progressive Scale Expansion Network
- COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation
- TextCaps : Handwritten Character Recognition with Very Small Datasets
- A Scalable Handwritten Text Recognition System
- FACLSTM: ConvLSTM with Focused Attention for Scene Text Recognition
- TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text
- Predictive Ensemble Learning with Application to Scene Text Detection
- Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding
- Selective Style Transfer for Text
- Towards Document Image Quality Assessment: A Text Line Based Framework and A Synthetic Text Line Image Dataset
- Omnidirectional Scene Text Detection with Sequential-free Box Discretization
- Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts
- ICDAR 2019 Competition on Scene Text Visual Question Answering
- Scene Text Magnifier
- ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
- Semi-Bagging Based Deep Neural Architecture to Extract Text from High Entropy Images
- RFBTD: RFB Text Detector
- SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
- GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
- 2D-CTC for Scene Text Recognition
- Generative Adversarial Network for Handwritten Text
- Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network
- 2D Attentional Irregular Scene Text Recognizer
- It's All About The Scale -- Efficient Text Detection Using Adaptive Scaling
- Automatic Text Line Segmentation Directly in JPEG Compressed Document Images
- Towards Pure End-to-End Learning for Recognizing Multiple Text Sequences from an Image
- Symmetry-constrained Rectification Network for Scene Text Recognition
- Editing Text in the Wild
- Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
- An End-to-end Video Text Detector with Online Tracking
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
- FaSTExt: Fast and Small Text Extractor
- Towards Unconstrained End-to-End Text Spotting
- Adaptive Embedding Gate for Attention-Based Scene Text Recognition
- End-To-End Measure for Text Recognition
- Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
- Focus-Enhanced Scene Text Recognition with Deformable Convolutions
- Alchemy: Techniques for Rectification Based Irregular Scene Text Recognition
- STELA: A Real-Time Scene Text Detector with Learned Anchor
- Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
- EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
- MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
- Next integrated result modelling for stopping the text field recognition process in a video using a result model with per-character alternatives
- On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
- Rosetta: Large scale system for text detection and recognition in images
- Scene Text Recognition with Temporal Convolutional Encoder
- Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory
- SA-Text: Simple but Accurate Detector for Text of Arbitrary Shapes
- Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks
- OmniTrack: Real-time detection and tracking of objects, text and logos in video
- DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images
- Learning to Predict More Accurate Text Instances for Scene Text Detection
- KISS: Keeping It Simple for Scene Text Recognition
- Real-time Scene Text Detection with Differentiable Binarization
- Methods of Weighted Combination for Text Field Recognition in a Video Stream
- Efficient Backbone Search for Scene Text Recognition
- Bidirectional Scene Text Recognition with a Single Decoder
- Patch Aggregator for Scene Text Script Identification
- A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
- TextSLAM: Visual SLAM with Planar Text Features
- Lifelong learning for text retrieval and recognition in historical handwritten document collections
- Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
- Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks
- MTRNet++: One-stage Mask-based Scene Text Eraser
- Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition
- Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection
- ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
- TreyNet: A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages
- Decoupled Attention Network for Text Recognition
- TextScanner: Reading Characters in Order for Robust Scene Text Recognition
- Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
- Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
- Fast Dense Residual Network: Enhancing Global Dense Feature Flow for Text Recognition
- Scene Text Recognition With Finer Grid Rectification
- GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition
- A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling
- Scale-Invariant Multi-Oriented Text Detection in Wild Scene Images
- Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
- ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
- Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
- Scene Text Recognition via Transformer
- ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation
- UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
- Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
- ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition
- ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
- Image Processing Based Scene-Text Detection and Recognition with Tesseract
- All you need is a second look: Towards Tighter Arbitrary shape text detection
- Text Recognition in the Wild: A Survey
- TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
- Realistic text replacement with non-uniform style conditioning
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
- OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
- Lyric Video Analysis Using Text Detection and Tracking
- On Vocabulary Reliance in Scene Text Recognition
- Large Scale Font Independent Urdu Text Recognition System
- RoadText-1K: Text Detection & Recognition Dataset for Driving Videos
- SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
- Self-Training for Domain Adaptive Scene Text Detection
- NENET: An Edge Learnable Network for Link Prediction in Scene Text
- Learning Robust Feature Representations for Scene Text Detection
- A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video
- Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition
- SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition
- Text Recognition in Real Scenarios with a Few Labeled Samples
- Text Detection on Roughly Placed Books by Leveraging a Learning-based Model Trained with Another Domain Data
- Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models
- Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval
- Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents
- Text Recognition -- Real World Data and Where to Find Them
- Maximum Entropy Regularization and Chinese Text Recognition
- FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection
- Privacy Preserving Text Recognition with Gradient-Boosting for Federated Learning
- RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
- Scene Text Detection with Selected Anchor
- Visual Attack and Defense on Text
- Complicating the Social Networks for Better Storytelling: An Empirical Study of Chinese Historical Text and Novel
- An End-to-End Attack on Text-based CAPTCHAs Based on Cycle-Consistent Generative Adversarial Network
- Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild
- A Hybrid Deep Learning Model for Arabic Text Recognition
- Unconstrained Text Detection in Manga: a New Dataset and Baseline
- Text-independent writer identification using convolutional neural network
- Adaptive Text Recognition through Visual Matching
- Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
- Character Region Attention For Text Spotting
- AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
- Fast Approximate Modelling of the Next Combination Result for Stopping the Text Recognition in a Video
- EASTER: Efficient and Scalable Text Recognizer
- Handwritten Script Identification from Text Lines
- Exploring Font-independent Features for Scene Text Recognition
- Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval
- Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition
- A Human Eye-based Text Color Scheme Generation Method for Image Synthesis
- Gaussian Constrained Attention Network for Scene Text Recognition
- TLGAN: document Text Localization using Generative Adversarial Nets
- Real-Time Text Detection and Recognition
- On-Device Language Identification of Text in Images using Diacritic Characters
- Digging Deeper into CRNN Model in Chinese Text Images Recognition
- Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering
- SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training
- BOTD: Bold Outline Text Detector
- Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm
- Boosting offline handwritten text recognition in historical documents with few labeled lines
- End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network
- MANGO: A Mask Attention Guided One-Stage Scene Text Spotter
- Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?
- Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network
- Scene Text Detection with Scribble Lines
- On Calibration of Scene-Text Recognition Models
- Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
- Enhancing Handwritten Text Recognition with N-gram sequence decomposition and Multitask Learning
- Research on All-content Text Recognition Method for Financial Ticket Image
- Scene Text Detection for Augmented Reality -- Character Bigram Approach to reduce False Positive Rate
- Research on Fast Text Recognition Method for Financial Ticket Image
- Robust Text CAPTCHAs Using Adversarial Examples
- Political Posters Identification with Appearance-Text Fusion
- Text Line Segmentation for Challenging Handwritten Document Images Using Fully Convolutional Network
- HANA: A HAndwritten NAme Database for Offline Handwritten Text Recognition
- Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models
- CSTR: A Classification Perspective on Scene Text Recognition
- Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links
- Urdu Handwritten Text Recognition Using ResNet18
- TS-Net: OCR Trained to Switch Between Text Transcription Styles
- Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
- Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection
- Tracking Based Semi-Automatic Annotation for Scene Text Videos
- Arbitrary-Shaped Text Detection withAdaptive Text Region Representation
- Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo
- MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
- Scene Text Retrieval via Joint Text Detection and Similarity Learning
- MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
- 1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit
- Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam
- RayNet: Real-time Scene Arbitrary-shape Text Detection with Multiple Rays
- ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment
- Bidirectional Regression for Arbitrary-Shaped Text Detection
- Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel
- SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
- Comprehensive Studies for Arbitrary-shape Scene Text Detection
- ICDAR 2021 Competition on Scene Video Text Spotting
- Towards the Unseen: Iterative Text Recognition by Distilling from Errors
- Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
- Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition
- Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection
- Why You Should Try the Real Data for the Scene Text Recognition
- IFR: Iterative Fusion Based Recognizer For Low Quality Scene Text Recognition
- MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
- Text-Aware Single Image Specular Highlight Removal
- Data Augmentation for Scene Text Recognition
- From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
- StackMix and Blot Augmentations for Handwritten Text Recognition
- Scene Text recognition with Full Normalization
- Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
- Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images
- PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
- Urdu text in natural scene images: a new dataset and preliminary text detection
- On Exploring and Improving Robustness of Scene Text Detection Models
- Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes
- ARTS: Eliminating Inconsistency between Text Detection and Recognition with Auto-Rectification Text Spotter
- TPSNet: Thin-Plate-Spline Representation for Arbitrary Shape Scene Text Detection
- FAST: Searching for a Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
- Contrastive Learning of Semantic and Visual Representations for Text Tracking
- SAFL: A Self-Attention Scene Text Recognizer with Focal Loss
- Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence
- Transfer Learning for Scene Text Recognition in Indian Languages
- Towards Boosting the Accuracy of Non-Latin Scene Text Recognition
- Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning
- AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks
- Importance of Textlines in Historical Document Classification
- Parallel Scale-wise Attention Network for Effective Scene Text Recognition
- PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
- TextAdaIN: Fine-Grained AdaIN for Robust Text Recognition
- Primitive Representation Learning for Scene Text Recognition
- An end-to-end Optical Character Recognition approach for ultra-low-resolution printed text images
- One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition
- MT: Multi-Perspective Feature Learning Network for Scene Text Detection
- Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition
- PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
- Rethinking Text Line Recognition Models
- TeLCoS: OnDevice Text Localization with Clustering of Script
- Line Segmentation from Unconstrained Handwritten Text Images using Adaptive Approach
- STRIDE : Scene Text Recognition In-Device
- I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition
- Vision Transformer for Fast and Efficient Scene Text Recognition
- LineCounter: Learning Handwritten Text Line Segmentation by Counting
- TRACE: A Differentiable Approach to Line-level Stroke Recovery for Offline Handwritten Text
- DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents
- Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter
- Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition
- Open Images V5 Text Annotation and Yet Another Mask Text Spotter
- All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection
- A Simple and Strong Baseline: Progressively Region-based Scene Text Removal Networks
- Recurrent neural network transducer for Japanese and Chinese offline handwritten text recognition
- Improving Structured Text Recognition with Regular Expression Biasing
- Adaptive Shrink-Mask for Text Detection
- Exploiting Multi-Scale Fusion, Spatial Attention and Patch Interaction Techniques for Text-Independent Writer Identification
- CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
- TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance
- Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages
- Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition
- Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
- Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection
- Natural Scene Text Editing Based on AI
- On-Device Spatial Attention based Sequence Learning Approach for Scene Text Script Identification
- Visual-Semantic Transformer for Scene Text Recognition
- A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
- Handwritten text generation and strikethrough characters augmentation
- CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning
- Self-paced learning to improve text row detection in historical documents with missing labels
- Arbitrary Shape Text Detection using Transformers
- A Glyph-driven Topology Enhancement Network for Scene Text Recognition
- Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting
- DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting
- Real-time Scene Text Detection Based on Global Level and Word Level Features
- Offline Text-Independent Writer Identification based on word level data
- Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
- Kernel Proposal Network for Arbitrary Shape Text Detection
- Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching
- APRNet: Attention-based Pixel-wise Rendering Network for Photo-Realistic Text Image Generation
- SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
- SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization
- End-to-End Video Text Spotting with Transformer
- Knowledge Mining with Scene Text for Fine-Grained Recognition
- Towards End-to-End Unified Scene Text Detection and Layout Analysis
- Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
- ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
- Text Spotting Transformers
- IterVM: Iterative Vision Modeling Module for Scene Text Recognition
- Aesthetic Text Logo Synthesis via Content-aware Layout Inferring
- Pushing the Performance Limit of Scene Text Recognizer without Human Annotation
- Self-Supervised Text Erasing with Controllable Image Synthesis
- Vision-Language Pre-Training for Boosting Scene Text Detectors
- SVTR: Scene Text Recognition with a Single Visual Model
- UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection
- TextMatcher: Cross-Attentional Neural Network to Compare Image and Text
- Text Detection & Recognition in the Wild for Robot Localization
- Easter2.0: Improving convolutional models for handwritten text recognition
- MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining
- Contrastive Graph Multimodal Model for Text Classification in Videos
- Transformer based Urdu Handwritten Text Optical Character Reader
- Text Detection on Technical Drawings for the Digitization of Brown-field Processes
- Multimodal Semi-Supervised Learning for Text Recognition
- BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line Segmentation
- Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition
- BusiNet -- a Light and Fast Text Detection Network for Business Documents
- Explore Faster Localization Learning For Scene Text Detection
- Detection of Furigana Text in Images
- Towards Multimodal Vision-Language Models Generating Non-Generic Text
- DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
- A Lexicon and Depth-wise Separable Convolution Based Handwritten Text Recognition System
- Scene Text Recognition with Permuted Autoregressive Sequence Models
- Decoupling Recognition from Detection: Single Shot Self-Reliant Scene Text Spotter
- 2D Self-Organized ONN Model For Handwritten Text Recognition
- Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
- SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition
- Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning
- Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition
- Runner-Up Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: Cropped Word Recognition
- GLASS: Global to Local Attention for Scene-Text Spotting
- Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions
- Shift Variance in Scene Text Detection
- DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection
- To show or not to show: Redacting sensitive text from videos of electronic displays
- TextTubes for Detecting Curved Text in the Wild
- ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
- On-Device Text Image Super Resolution
- TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
- TextSR: Content-Aware Text Super-Resolution Guided by Recognition
- Text Detection and Recognition in the Wild: A Review
- C3-STISR: Scene Text Image Super-resolution with Triple Clues
- Fastext: Efficient unconstrained scene text detector - 1214.[[code](https://github.com/MichalBusta/FASText)]
-
-
Datasets
- www.iapr-tc11.org
- tc11.cvc.uab.es
- `2017 COCO-Text`
- `2017 DeTEXT`
- `2017 DOST`
- `2017 FSNS`
- `2017 MLT`
- `2017 IEHHR`
- `2011-2015 Born-DIgitalImage`
- `2013-2015 Focused Scene Text`
- `2013-2015 Text in Videos`
- `2015 Incidental Scene Text`
- ICDAR Chinese
- `Chinese Text in the Wild`
- `COCO-Text (Computer Vision Group, Cornell)`
- `USTB-SV1k`
- `download`
- `IIIT 5K-Words`
- `download`
- `StanfordSynth(Stanford, AI Group)`
- `download`
- `MSRA Text Detection 500 Database (MSRA-TD500)`
- `OSTD`
- `Traffice Guide Panel Text Dataset,TGPT`
- `Street View Text (SVT)`
- `KAIST Scene_Text Database`
- `Chars74k`
- ICDAR 2015 - library/manual/10735/paper-icon_1150845_tmb.jpg)](http://rrc.cvc.uab.es/files/Robust-Reading-Competition-Karatzas.pdf)|
- ICDAR 2013 - library/manual/10735/paper-icon_1150845_tmb.jpg)](http://dagdata.cvc.uab.es/icdar2013competition/files/icdar2013_competition_report.pdf)|
- ICDAR 2011 - library/manual/10735/paper-icon_1150845_tmb.jpg)](http://www.iapr-tc11.org/archive/icdar2011/fileup/PDF/4520b491.pdf)|
- ICDAR 2005 - library/manual/10735/paper-icon_1150845_tmb.jpg)](http://www.academia.edu/download/30700479/10.1.1.96.4332.pdf)|
- ICDAR 2003 - library/manual/10735/paper-icon_1150845_tmb.jpg)](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.332.3461&rep=rep1&type=pdf)|
Categories
Sub Categories