{"id":13543132,"url":"https://github.com/YukangWang/TextField","last_synced_at":"2025-04-02T12:31:41.648Z","repository":{"id":127927541,"uuid":"162658256","full_name":"YukangWang/TextField","owner":"YukangWang","description":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection (TIP 2019)","archived":false,"fork":false,"pushed_at":"2019-03-15T12:43:15.000Z","size":2485,"stargazers_count":100,"open_issues_count":7,"forks_count":25,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-11-03T10:32:06.597Z","etag":null,"topics":["scene-text","text-detection"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YukangWang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-12-21T03:00:19.000Z","updated_at":"2024-08-06T05:52:22.000Z","dependencies_parsed_at":null,"dependency_job_id":"5a4a1694-a1d0-42ed-9fc2-8ebcc79cb3b9","html_url":"https://github.com/YukangWang/TextField","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/YukangWang%2FTextField","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YukangWang%2FTextField/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YukangWang%2FTextField/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YukangWang%2FTextField/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YukangWang","download_url":"https://codeload.github.com/YukangWang/TextField/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246815649,"owners_count":20838476,"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":["scene-text","text-detection"],"created_at":"2024-08-01T11:00:23.770Z","updated_at":"2025-04-02T12:31:36.638Z","avatar_url":"https://github.com/YukangWang.png","language":"C++","readme":"# TextField: Learning A Deep Direction Field for Irregular Scene Text Detection\n\n## Introduction\n\nThe code and trained models of: \n\nTextField: Learning A Deep Direction Field for Irregular Scene Text Detection, TIP 2019 [[Paper]](https://arxiv.org/abs/1812.01393)\n\n## Citation\n\nPlease cite the related works in your publications if it helps your research:\n\n```\n\n@article{xu2018textfield,\n  title={TextField: Learning A Deep Direction Field for Irregular Scene Text Detection},\n  author={Xu, Yongchao and Wang, Yukang and Zhou, Wei and Wang, Yongpan and Yang, Zhibo and Bai, Xiang},\n  journal={arXiv preprint arXiv:1812.01393},\n  year={2018}\n}\n\n```\n\n## Prerequisite\n\n* Caffe and SynthText pretrained model [[Link]](https://drive.google.com/file/d/1C4EUllZMTNYt_Q2t4PjZypepYjHechvj/view?usp=sharing)\n\n* Datasets: [[Total-Text]](http://www.cs-chan.com/source/ICDAR2017/totaltext.zip), [[ICDAR2015]](http://rrc.cvc.uab.es/?ch=4\u0026com=downloads)\n\n* OpenCV 3.4.3\n\n* MATLAB\n\n\n## Usage\n\n#### 1. Install Caffe\n\n```bash\n\ncp Makefile.config.example Makefile.config\n# adjust Makefile.config (for example, enable python layer)\nmake all -j16\n# make sure to include $CAFFE_ROOT/python to your PYTHONPATH.\nmake pycaffe\n\n```\nPlease refer to [Caffe Installation](http://caffe.berkeleyvision.org/install_apt.html) to ensure other dependencies.\n\n#### 2. Data and model preparation\n\n```bash\n\n# download datasets and pretrained model then\nmkdir data \u0026\u0026 mv [your_dataset_folder] data/\nmkdir models \u0026\u0026 mv [your_pretrained_model] models/\n\n```  \n\n#### 3. Training scripts\n  \n\n```bash\n\n# an example on Total-Text dataset\ncd examples/TextField/\npython train.py --gpu [your_gpu_id] --dataset total --initmodel ../../models/synth_iter_800000.caffemodel\n\n```\n\n#### 4. Evaluation scripts\n\n```bash\n\n# an example on Total-Text dataset\ncd evaluation/total/\n./eval.sh\n\n```\n\n## Results and Trained Models\n\n#### Total-Text\n\n| Recall | Precision | F-measure | Link |\n|:-------------:|:-------------:|:-------------:|:-----:|\n| 0.816 | 0.824 | 0.820 | [[Google drive]](https://drive.google.com/file/d/1FAiL2C0WOuN5QFSD6wfLSgP29mmBUdIV/view?usp=sharing) |\n\n\u003e*lambda=0.50 for post-processing\n\n#### ICDAR2015\n\n| Recall | Precision | F-measure | Link |\n|:-------------:|:-------------:|:-------------:|:-----:|\n| 0.811 | 0.846 | 0.828 | [[Google drive]](https://drive.google.com/file/d/1T6lBbe1BXfppsuijZTE_LSaH1XT_5_jD/view?usp=sharing) |\n\n\u003e*lambda=0.75 for post-processing\n","funding_links":[],"categories":["Text detection and localization","Appendix: Object Detection for Natural Scene"],"sub_categories":["Form Segmentation","Papers"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYukangWang%2FTextField","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYukangWang%2FTextField","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYukangWang%2FTextField/lists"}