Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/ViTAE-Transformer/SAMText

The official repo for the technical report "Scalable Mask Annotation for Video Text Spotting"
https://github.com/ViTAE-Transformer/SAMText

dataset deep-learning sam scene-text-spotting segment-anything-model video-text-spotting

Last synced: 20 days ago
JSON representation

The official repo for the technical report "Scalable Mask Annotation for Video Text Spotting"

Awesome Lists containing this project

README 

        
 Scalable Mask Annotation for Video Text Spotting 




This is the official repository of the paper Scalable Mask Annotation for Video Text Spotting.


Haibin He, Jing Zhang, Mengyang Xu, Juhua Liu, Bo Du, Dacheng Tao




  News |

  Abstract |

  Method |

  Usage |

  Results |

  Statement




# News



***02/05/2023***



- The paper is post on arxiv! The code will be made public available once cleaned up.



- Relevant Project: 



  > [**DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer** ](https://arxiv.org/abs/2207.04491) | [Code](https://github.com/ymy-k/DPText-DETR)

  >

  > Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Bo Du, Dacheng Tao

  >

  > [**DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting** ](https://arxiv.org/pdf/2211.10772v3) | [Code](https://github.com/ViTAE-Transformer/DeepSolo)

  >

  > Maoyuan Ye,  Jing Zhang, Shanshan Zhao, Juhua Liu, Tongliang Liu, Bo Du, Dacheng Tao

  >

  > [**I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection** ](https://arxiv.org/abs/2108.01343) | [Code](https://github.com/ViTAE-Transformer/I3CL)

  >

  > Bo Du, Jian Ye, Jing Zhang, Juhua Liu, Dacheng Tao



  Other applications of [ViTAE](https://github.com/ViTAE-Transformer/ViTAE-Transformer) inlcude: [ViTPose](https://github.com/ViTAE-Transformer/ViTPose) | [Remote Sensing](https://github.com/ViTAE-Transformer/ViTAE-Transformer-Remote-Sensing) | [Matting](https://github.com/ViTAE-Transformer/ViTAE-Transformer-Matting) | [VSA](https://github.com/ViTAE-Transformer/ViTAE-VSA) | [Video Object Segmentation](https://github.com/ViTAE-Transformer/VOS-LLB)



# Abstract



Video text spotting refers to localizing, recognizing, and tracking textual elements

such as captions, logos, license plates, signs, and other forms of text within consecutive

video frames. However, current datasets available for this task rely on

quadrilateral ground truth annotations, which may result in including excessive

background content and inaccurate text boundaries. Furthermore, methods trained

on these datasets often produce prediction results in the form of quadrilateral boxes,

which limits their ability to handle complex scenarios such as dense or curved text.

To address these issues, we propose a scalable mask annotation pipeline called

SAMText for video text spotting.SAMText leverages the SAM model to

generate mask annotations for scene text images or video frames at scale. Using

SAMText, we have created a large-scale dataset, SAMText-9M, that contains over

2,400 video clips sourced from existing datasets and over 9 million mask annotations.

We have also conducted a thorough statistical analysis of the generated

masks and their quality, identifying several research topics that could be further

explored based on this dataset. 



# Method





Figure 1: Overview of the SAMText pipeline that builds upon the SAM   approach to generate

mask annotations for scene text images or video frames at scale. The input bounding box may be

sourced from existing annotations or derived from a scene text detection model.



# Usage

The code and dataset will be released soon.



# Results

# The Quality of Generated Masks





Figure 3: The distribution of IoU between the generated

masks and ground truth masks in the COCOText

training dataset:  COCO_Text V2  

 



To evaluate the performance of SAMText, we

select the COCO-Text training dataset [25] as it

provides ground truth mask annotations for text

instances. Specifically, we randomly sample

10% of the training data and calculate the IoU

between the masks generated by SAMText and

their corresponding ground truth masks. Our

findings show that SAMText has high accuracy,

with an average IoU of 0.70.  Figure 3 presents

the histogram of IoU scores. Notably, the majority

of IoU scores are centered around 0.75,

suggesting that SAMText performs well.



# Visualization of Generated Masks





Figure 2: Some visualization results of the generated masks in five datasets using the SAMText

pipeline. The top row shows the scene text frames while the bottom row shows the generated masks.  

 



In Figure 2, we show some visualization results of the generated masks in five datasets using the

SAMText pipeline. The top row shows the scene text frames while the bottom row shows the

generated masks. As can be seen, the generated masks possess fewer background components and

align more precisely with the text boundaries than the bounding boxes. As a result, the generated

mask annotations facilitate conducting more comprehensive research on this dataset, e.g., video text

segmentation and video text spotting using mask annotations.



## Dataset Statistics and Analysis

### The size distribution.





Figure 4: (a) The mask size distributions of the ICDAR15, RoadText-1k, LSVDT, and DSText datasets.

Masks exceeding 10,000 pixels are excluded from the statistics. (b) The mask size distributions of

the BOVText datasets. Masks exceeding 80,000 pixels are excluded from the statistics.  

 



### The IoU and COV distribution.





Figure 5: (a) The distribution of IoU between the generated masks and ground truth bounding boxes

in each dataset. (b) The CoV distribution of mask size changes for the same individual in consecutive

frames in all five datasets, excluding the CoV scores exceeding 1.0 from the statistics.  

 



### The spatial distribution.





Figure 6: Visualization of the heatmaps that depict the spatial distribution of the generated masks in

the five video text spotting datasets employed to establish SAMText-9M.  

 



# Statement



This project is for research purpose only. For any other questions please contact [[email protected]](mailto:[email protected]).



## Citation



If you find SAMText helpful, please consider giving this repo a star:star: and citing:



```

@inproceedings{SAMText,

  title={Scalable Mask Annotation for Video Text Spotting},

  author={Haibin He, Jing Zhang, Mengyang Xu, Juhua Liu, Bo Du, Dacheng Tao},

  booktitle={arxiv},

  year={arXiv preprint arXiv:2305.01443}

}

```