{"id":13543155,"url":"https://github.com/clovaai/CRAFT-pytorch","last_synced_at":"2025-04-02T12:31:41.077Z","repository":{"id":38421544,"uuid":"190153979","full_name":"clovaai/CRAFT-pytorch","owner":"clovaai","description":"Official implementation of Character Region Awareness for Text Detection (CRAFT)","archived":false,"fork":false,"pushed_at":"2024-07-16T04:32:12.000Z","size":1730,"stargazers_count":3221,"open_issues_count":114,"forks_count":921,"subscribers_count":70,"default_branch":"master","last_synced_at":"2025-03-27T06:07:11.528Z","etag":null,"topics":["craft","curved-text","cvpr2019","detection","ocr","ocr-detection","pytorch","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/clovaai.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-06-04T07:43:58.000Z","updated_at":"2025-03-23T18:20:48.000Z","dependencies_parsed_at":"2024-11-03T10:30:21.338Z","dependency_job_id":"67c5b032-5c7f-4207-beab-c2f42933ad27","html_url":"https://github.com/clovaai/CRAFT-pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clovaai%2FCRAFT-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clovaai%2FCRAFT-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clovaai%2FCRAFT-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/clovaai%2FCRAFT-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/clovaai","download_url":"https://codeload.github.com/clovaai/CRAFT-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246815632,"owners_count":20838474,"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":["craft","curved-text","cvpr2019","detection","ocr","ocr-detection","pytorch","text-detection"],"created_at":"2024-08-01T11:00:24.391Z","updated_at":"2025-04-02T12:31:36.068Z","avatar_url":"https://github.com/clovaai.png","language":"Python","funding_links":[],"categories":["Text detection and localization","Python","Projects","Text Detection"],"sub_categories":["CRAFT [paper:2019](https://arxiv.org/pdf/1904.01941.pdf)","Global AI Projects","2019"],"readme":"## CRAFT: Character-Region Awareness For Text detection\nOfficial Pytorch implementation of CRAFT text detector | [Paper](https://arxiv.org/abs/1904.01941) | [Pretrained Model](https://drive.google.com/open?id=1Jk4eGD7crsqCCg9C9VjCLkMN3ze8kutZ) | [Supplementary](https://youtu.be/HI8MzpY8KMI)\n\n**[Youngmin Baek](mailto:youngmin.baek@navercorp.com), Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee.**\n \nClova AI Research, NAVER Corp.\n\n### Sample Results\n\n### Overview\nPyTorch implementation for CRAFT text detector that effectively detect text area by exploring each character region and affinity between characters. The bounding box of texts are obtained by simply finding minimum bounding rectangles on binary map after thresholding character region and affinity scores. \n\n\u003cimg width=\"1000\" alt=\"teaser\" src=\"./figures/craft_example.gif\"\u003e\n\n## Updates\n**13 Jun, 2019**: Initial update\n**20 Jul, 2019**: Added post-processing for polygon result\n**28 Sep, 2019**: Added the trained model on IC15 and the link refiner\n\n\n## Getting started\n### Install dependencies\n#### Requirements\n- PyTorch\u003e=0.4.1\n- torchvision\u003e=0.2.1\n- opencv-python\u003e=3.4.2\n- check requiremtns.txt\n```\npip install -r requirements.txt\n```\n\n### Training\nThe code for training is not included in this repository, and we cannot release the full training code for IP reason.\n\n\n### Test instruction using pretrained model\n- Download the trained models\n \n *Model name* | *Used datasets* | *Languages* | *Purpose* | *Model Link* |\n | :--- | :--- | :--- | :--- | :--- |\nGeneral | SynthText, IC13, IC17 | Eng + MLT | For general purpose | [Click](https://drive.google.com/open?id=1Jk4eGD7crsqCCg9C9VjCLkMN3ze8kutZ)\nIC15 | SynthText, IC15 | Eng | For IC15 only | [Click](https://drive.google.com/open?id=1i2R7UIUqmkUtF0jv_3MXTqmQ_9wuAnLf)\nLinkRefiner | CTW1500 | - | Used with the General Model | [Click](https://drive.google.com/open?id=1XSaFwBkOaFOdtk4Ane3DFyJGPRw6v5bO)\n\n* Run with pretrained model\n``` (with python 3.7)\npython test.py --trained_model=[weightfile] --test_folder=[folder path to test images]\n```\n\nThe result image and socre maps will be saved to `./result` by default.\n\n### Arguments\n* `--trained_model`: pretrained model\n* `--text_threshold`: text confidence threshold\n* `--low_text`: text low-bound score\n* `--link_threshold`: link confidence threshold\n* `--cuda`: use cuda for inference (default:True)\n* `--canvas_size`: max image size for inference\n* `--mag_ratio`: image magnification ratio\n* `--poly`: enable polygon type result\n* `--show_time`: show processing time\n* `--test_folder`: folder path to input images\n* `--refine`: use link refiner for sentense-level dataset\n* `--refiner_model`: pretrained refiner model\n\n\n## Links\n- WebDemo : https://demo.ocr.clova.ai/\n- Repo of recognition : https://github.com/clovaai/deep-text-recognition-benchmark\n\n## Citation\n```\n@inproceedings{baek2019character,\n  title={Character Region Awareness for Text Detection},\n  author={Baek, Youngmin and Lee, Bado and Han, Dongyoon and Yun, Sangdoo and Lee, Hwalsuk},\n  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},\n  pages={9365--9374},\n  year={2019}\n}\n```\n\n## License\n```\nCopyright (c) 2019-present NAVER Corp.\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in\nall copies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN\nTHE SOFTWARE.\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclovaai%2FCRAFT-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fclovaai%2FCRAFT-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclovaai%2FCRAFT-pytorch/lists"}