Ecosyste.ms: Awesome

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

https://github.com/rahzaazhar/PAN-PSEnet

Pytorch implementation of PSEnet with Pyramid Attention Network as feature extractor
https://github.com/rahzaazhar/PAN-PSEnet

deep-learning scene-text-detection

Last synced: 3 months ago
JSON representation

Pytorch implementation of PSEnet with Pyramid Attention Network as feature extractor

Host: GitHub
URL: https://github.com/rahzaazhar/PAN-PSEnet
Owner: rahzaazhar
License: apache-2.0
Created: 2019-07-26T09:43:29.000Z (almost 5 years ago)
Default Branch: latest
Last Pushed: 2020-09-05T12:04:09.000Z (almost 4 years ago)
Last Synced: 2024-01-16T02:48:33.494Z (5 months ago)
Topics: deep-learning, scene-text-detection
Language: Python
Homepage:
Size: 4.62 MB
Stars: 62
Watchers: 7
Forks: 32
Open Issues: 3
Metadata Files:
- Readme: README.md
- License: LICENSE

Lists

awesome-ocr - PAN-PSEnet
awesome-ocr - PAN-PSEnet

README

# Scene Text-Spotting based on PSEnet+CRNN

Pytorch implementation of an end to end Text-Spotter with a PSEnet text detector and CRNN text recognizer. We plan to grow this repository into an open research platform for multi-lingual text detection and recognition from natural scene images, targeted towards low-resource languages.

## Requirements
- Python 3.6.5
- Pytorch 1.2
- pyclipper
- Polygon 3.0.8
- OpenCV 3.4.1

### Demo
- Download the trained CRNN and PSEnet models from the links provided below.
- Copy paths of the models and paste them in params.py
- run end-end.py
```
python end-end.py --img [path to image] --e2e_config_name [end to end config name]
```

### Pre-trained Models

Both PSEnet and CRNN pre-trained models can be found here: [gdrive](https://drive.google.com/open?id=1Bza5tAACtqtLNLxg7ws6rzRrSeW1-Jp6)

* the PSEnet model is a multi-lingual text detector, trained on MLT 2019. Works quite well!
* the CRNN recognizes Hindi, Bangla, Malayalam, Kanada, Tamil, Telugu, Odia, Sanskrit, Marathi!

Download the models in `models/` directory and modify `params.py` if required.

### Training instructions
* To train your own detection model refer to [this](Detection/PSEnet/train_ic19MLT.py) file.
* To train your own recognition model refer to [this](Recognition/Readme.md) file.

### Samples

![Original Image](./demo/tr_img_09961.jpg)

![After Text Detection](./demo/result.jpg)

![After Text Recognition](./demo/recog_result.png)

### Contributors

* Azhar Shaikh, PES University [LinkedIn](https://www.linkedin.com/in/azhar-shaikh-b61892137)
* Nishant Sinha, [OffNote Labs](https://github.com/ofnote)

Work done as part of Internship with [OffNote Labs](http://offnote.co).

### References
1. [https://github.com/whai362/PSENet](https://github.com/whai362/PSENet)
2. [https://github.com/Holmeyoung/crnn-pytorch](https://github.com/Holmeyoung/crnn-pytorch)

**If this repository helps you, please star it. Thank you!**