Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-deep-text-detection-recognition
A curated list of resources for text detection/recognition (optical character recognition ) with deep learning methods.
https://github.com/hwalsuklee/awesome-deep-text-detection-recognition
Last synced: 5 days ago
JSON representation
-
Text Detection
- WordSup: Exploiting Word Annotations for Character based Text Detection
- Text-Attentional Convolutional Neural Networks for Scene Text Detection
- Multi-Oriented Text Detection with Fully Convolutional Networks
- Symmetry-based text line detection in natural scenes
- Text-Attentional Convolutional Neural Networks for Scene Text Detection
- Text Flow : A Unified Text Detection System in Natural Scene Images
- Accurate Text Localization in Natural Image with Cascaded Convolutional TextNetwork
- Multi-Oriented Text Detection with Fully Convolutional Networks
- Synthetic Data for Text Localisation in Natural Images - me/SynthText) <br> [`DB`](http://www.robots.ox.ac.uk/~vgg/data/scenetext/)
- Scene Text Detection Via Holistic, Multi-Channel Prediction
- Detecting Text in Natural Image with Connectionist Text Proposal Network - detection-ctpn) <br> [`TF`](https://github.com/Li-Ming-Fan/OCR-DETECTION-CTPN) <br> [`DEMO`](http://textdet.com/) <br> [`BLOG(CH)`](http://slade-ruan.me/2017/10/22/text-detection-ctpn/)
- 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 - seglink-spotlight-CVPR17.pdf) <br> [`VIDEO`](https://www.youtube.com/watch?v=w0vZWUi-m0c) |
- 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
- WordFence: Text Detection in Natural Images with Border Awareness
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection - RCNN_Tensorflow) <br> [`CAFFE(M)`](https://github.com/beacandler/R2CNN)
- Multi-scale FCN with Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting In The Wild
- Deep Scene Text Detection with Connected Component Proposals
- Single Shot Text Detector with Regional Attention - k)
- Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
- WeText: Scene Text Detection under Weak Supervision
- Deep Residual Text Detection Network for Scene Text
- Feature Enhancement Network: A Refined Scene Text Detector
- ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
- PixelLink: Detecting Scene Text via Instance Segmentation
- Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
- Rotation-Sensitive Regression for Oriented Scene Text Detection
- Detecting Multi-Oriented Text with Corner-based Region Proposals
- 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
- Shape Robust Text Detection with Progressive Scale Expansion Network
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
- Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
- Scene Text Detection with Supervised Pyramid Context Network
- TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
- Towards Robust Curve Text Detection with Conditional Spatial Expansion
- Shape Robust Text Detection with Progressive Scale Expansion Network
- Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes Screen reader support enabled
- Learning Shape-Aware Embedding for Scene Text Detection
- Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation
- Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
- Geometry Normalization Networks for Accurate Scene Text Detection
- Real-time Scene Text Detection with Differentiable Binarization
- leader-board
- Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees
- Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
- ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
- Character Region Awareness for Text Detection - pytorch) <br> [`VIDEO`](https://www.youtube.com/watch?v=HI8MzpY8KMI) <br> [`PYTORCH`](https://github.com/guruL/Character-Region-Awareness-for-Text-Detection-) <br> [`TF(M)`](https://github.com/namedysx/CRAFT-tensorflow) <br> [`KERAS`](https://github.com/RubanSeven/CRAFT_keras) <br> [`BLOG_CH`](https://medium.com/@xiaosean5408/craft簡介-character-region-awareness-for-text-detection-a5c782408f00) <br> [`BLOG_KR`](https://data-newbie.tistory.com/187) <br> [`BLOG_KR`](https://medium.com/qandastudy/character-region-awareness-for-text-detection-craft-review-a7542779e037) <br> [`BLOG_KR`](https://github.com/chullhwan-song/Reading-Paper/issues/136)|
- Single Shot Text Detector with Regional Attention - k)
- WeText: Scene Text Detection under Weak Supervision
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection - RCNN_Tensorflow) <br> [`CAFFE(M)`](https://github.com/beacandler/R2CNN)
- Detecting Multi-Oriented Text with Corner-based Region Proposals
- Shape Robust Text Detection with Progressive Scale Expansion Network
-
Text Recognition
- Deep structured output learning for unconstrained text recognition
- Reading Scene Text in Deep Convolutional Sequences
- An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition - CV/CRNN_Tensorflow) <br> [`TF`](https://github.com/bai-shang/OCR_TF_CRNN_CTC) <br> [`PYTORCH`](https://github.com/meijieru/crnn.pytorch) <br> [`PYTORCH(M)`](https://github.com/BelBES/crnn-pytorch) <br> [`BLOG(KR)`](https://medium.com/@mldevhong/%EB%85%BC%EB%AC%B8-%EB%B2%88%EC%97%AD-rcnn-an-end-to-end-trainable-neural-network-for-image-based-sequence-recognition-and-its-f6456886d6f8)
- Recursive Recurrent Nets with Attention Modeling for OCR in the Wild
- Robust scene text recognition with automatic rectification
- CNN-N-Gram for Handwriting Word Recognition
- STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition
- STN-OCR: A single Neural Network for Text Detection and Text Recognition - ocr) <br> [`PRJ`](https://bartzi.de/research/stn-ocr) <br> [`BLOG`](https://medium.com/@Synced/stn-ocr-a-single-neural-network-for-text-detection-and-text-recognition-220debe6ded4)
- Learning to Read Irregular Text with Attention Mechanisms
- Scene Text Recognition with Sliding Convolutional Character Models
- Focusing Attention: Towards Accurate Text Recognition in Natural Images
- AON: Towards Arbitrarily-Oriented Text Recognition
- Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition
- SqueezedText: A Real-time Scene Text Recognition by Binary Convolutional Encoder-decoder Network
- Edit Probability for Scene Text Recognition
- Scene Text Recognition from Two-Dimensional Perspective
- Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition - Strong-Baseline-for-Text-Recognition)
- ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification
- MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition - Luo/MORAN_v2)
- What is wrong with scene text recognition model comparisons? dataset and model analysis - text-recognition-benchmark) <br> [`BLOG_KR`](https://data-newbie.tistory.com/156)
- Aggregation Cross-Entropy for Sequence Recognition - Cross-Entropy) |
- Symmetry-constrained Rectification Network for Scene Text Recognition
- TextScanner: Reading Characters in Order for Robust Scene Text Recognition
- Decoupled Attention Network for Text Recognition - Tianwei/Decoupled-attention-network)
- GTC: Guided Training of CTC
- STN-OCR: A single Neural Network for Text Detection and Text Recognition - ocr) <br> [`PRJ`](https://bartzi.de/research/stn-ocr) <br> [`BLOG`](https://medium.com/@Synced/stn-ocr-a-single-neural-network-for-text-detection-and-text-recognition-220debe6ded4)
- Deep structured output learning for unconstrained text recognition
- Scene Text Recognition with Sliding Convolutional Character Models
-
End-to-End Text Recognition
- End-to-end text recognition with convolutional neural networks
- Deep Features for Text Spotting
- Real-time Lexicon-free Scene Text Localization and Recognition
- TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild
- Towards End-to-end Text Spotting with Convolution Recurrent Neural Network
- Towards Unconstrained End-to-End Text Spotting - Unconstrained-End-to-End-Text-Spotting-0c66c692950f458e9a1323db2a79d143)
- Convolutional Character Networks - charnet)
- All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
- Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
- FOTS: Fast Oriented Text Spotting with a Unified Network
- TextBoxes: A fast text detector with a single deep neural network
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
- An end-to-end TextSpotter with Explicit Alignment and Attention
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
- ASTER: An Attentional Scene Text Recognizer with Flexible Rectification
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- Towards End-to-end Text Spotting with Convolution Recurrent Neural Network
- TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild
- An end-to-end TextSpotter with Explicit Alignment and Attention
-
Others
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- End-to-End Interpretation of the French Street Name Signs Dataset
- Attention-based Extraction of Structured Information from Street View Imagery - OCR) <br> [`TF`](https://github.com/emedvedev/attention-ocr) <br> [`LUA`](https://github.com/da03/torch-Attention-OCR) <br> [`BLOG_KR`](https://norman3.github.io/papers/docs/attention_ocr.html)
- Unambiguous Text Localization and Retrieval for Cluttered Scenes
- Detection and Recognition of Text Embedded in Online Images via Neural Context Models
- Separating Style and Content for Generalized Style Transfer
- Detecting Curve Text in the Wild New Dataset and New Solution - Liu/Curve-Text-Detector)
- SEE: Towards Semi-Supervised End-to-End Scene Text Recognition
- Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networks
- Document Enhancement using Visibility Detection - Graphics-Multimedia/Software/VisibilityDetection/)
- Multi-Task Handwritten Document Layout Analysis
- Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes - Image-Synthesis-for-Accurate-Detection-and-Recognition-of-Texts-in-Scenes)
- EnsNet: Ensconce Text in the Wild - Text-Removal)
- Spatial Fusion GAN for Image Synthesis - GAN)
- Hierarchical Encoder with Auxiliary Supervision for Table-to-text Generation: Learning Better Representation for Tables
- A Radical-aware Attention-based Model for Chinese Text Classification
- Handwriting Recognition in Low-resource Scripts using Adversarial Learning
- Tightness-aware Evaluation Protocol for Scene Text Detection - Liu/TIoU-metric)
- Scene Text Visual Question Answering
- DynTypo: Example-based Dynamic Text Effects Transfer - o)
- Typography with Decor: Intelligent Text Style Transfer
- An Alternative Deep Feature Approach to Line Level Keyword Spotting
- GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition
- Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
- Large-scale Tag-based Font Retrieval with Generative Feature Learning
- TextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts
- DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks - stonybrook/DewarpNet)
- Scene Text Visual Question Answering
- DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks - stonybrook/DewarpNet)
- DocUNet: Document Image Unwarping via A Stacked U-Net
-
Other lists
-
Tutorial Materials
- Irregular Text Detection and Recognition (CBDAR2019 keynote)
- Deep Neural Networks for Scene Text Reading (IC17 Keynote)
- Oriented Scene Text Detection Revisited (VALSE17 Invited Talk)
- Scene Text Detection and Recognition (Joint course of Megvii Inc. & Peking Univ.)
- Classic Text Detectors
- Scene text detection and recognition: recent advances and future trends
- Scene text detection and recognition: recent advances and future trends
Categories
Sub Categories