{"id":13543218,"url":"https://github.com/rahzaazhar/PAN-PSEnet","last_synced_at":"2025-04-02T12:31:51.669Z","repository":{"id":169689349,"uuid":"198990845","full_name":"rahzaazhar/PAN-PSEnet","owner":"rahzaazhar","description":"Pytorch implementation of PSEnet with Pyramid Attention Network as feature extractor","archived":false,"fork":false,"pushed_at":"2020-09-05T12:04:09.000Z","size":4840,"stargazers_count":63,"open_issues_count":3,"forks_count":32,"subscribers_count":7,"default_branch":"latest","last_synced_at":"2024-11-03T10:32:08.357Z","etag":null,"topics":["deep-learning","scene-text-detection"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rahzaazhar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-07-26T09:43:29.000Z","updated_at":"2024-09-11T06:32:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"89e277fd-79eb-4fd7-adc8-adfe79b0deec","html_url":"https://github.com/rahzaazhar/PAN-PSEnet","commit_stats":null,"previous_names":["rahzaazhar/pan-psenet"],"tags_count":0,"template":true,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahzaazhar%2FPAN-PSEnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahzaazhar%2FPAN-PSEnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahzaazhar%2FPAN-PSEnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahzaazhar%2FPAN-PSEnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rahzaazhar","download_url":"https://codeload.github.com/rahzaazhar/PAN-PSEnet/tar.gz/refs/heads/latest","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246815726,"owners_count":20838494,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","scene-text-detection"],"created_at":"2024-08-01T11:00:26.405Z","updated_at":"2025-04-02T12:31:46.660Z","avatar_url":"https://github.com/rahzaazhar.png","language":"Python","funding_links":[],"categories":["Text detection and localization"],"sub_categories":["PSENet [paper:2018](https://arxiv.org/pdf/1806.02559.pdf)"],"readme":"# Scene Text-Spotting based on PSEnet+CRNN\n\nPytorch 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.\n\n## Requirements\n- Python 3.6.5\n- Pytorch 1.2\n- pyclipper\n- Polygon 3.0.8\n- OpenCV 3.4.1\n\n### Demo\n- Download the trained CRNN and PSEnet models from the links provided below.\n- Copy paths of the models and paste them in params.py\n- run end-end.py\n```\npython end-end.py --img [path to image] --e2e_config_name [end to end config name]\n```\n\n### Pre-trained Models\n\nBoth PSEnet and CRNN pre-trained models can be found here: [gdrive](https://drive.google.com/open?id=1Bza5tAACtqtLNLxg7ws6rzRrSeW1-Jp6)\n\n* the PSEnet model is a multi-lingual text detector, trained on MLT 2019. Works quite well!\n* the CRNN recognizes Hindi, Bangla, Malayalam, Kanada, Tamil, Telugu, Odia, Sanskrit, Marathi!\n\nDownload the models in `models/` directory and modify `params.py` if required.\n\n### Training instructions\n* To train your own detection model refer to [this](Detection/PSEnet/train_ic19MLT.py) file.\n* To train your own recognition model refer to [this](Recognition/Readme.md) file.\n\n### Samples\n\n![Original Image](./demo/tr_img_09961.jpg)\n\n![After Text Detection](./demo/result.jpg)\n\n![After Text Recognition](./demo/recog_result.png)\n\n### Contributors\n\n* Azhar Shaikh, PES University [LinkedIn](https://www.linkedin.com/in/azhar-shaikh-b61892137)\n* Nishant Sinha, [OffNote Labs](https://github.com/ofnote)\n\nWork done as part of Internship with [OffNote Labs](http://offnote.co).\n\n### References\n1. [https://github.com/whai362/PSENet](https://github.com/whai362/PSENet)\n2. [https://github.com/Holmeyoung/crnn-pytorch](https://github.com/Holmeyoung/crnn-pytorch)\n\n**If this repository helps you, please star it. Thank you!**\n\n\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frahzaazhar%2FPAN-PSEnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frahzaazhar%2FPAN-PSEnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frahzaazhar%2FPAN-PSEnet/lists"}