{"id":15043508,"url":"https://github.com/breta01/handwriting-ocr","last_synced_at":"2025-04-12T19:42:54.370Z","repository":{"id":47589267,"uuid":"78966987","full_name":"Breta01/handwriting-ocr","owner":"Breta01","description":"OCR software for recognition of handwritten text","archived":false,"fork":false,"pushed_at":"2022-12-23T08:43:21.000Z","size":532191,"stargazers_count":793,"open_issues_count":81,"forks_count":243,"subscribers_count":28,"default_branch":"master","last_synced_at":"2025-04-03T22:09:54.604Z","etag":null,"topics":["handwriting-ocr","machine-learning","ocr","opencv","python","recognition","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Breta01.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null},"funding":{"github":"Breta01","patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"custom":"https://paypal.me/bretahajek/20"}},"created_at":"2017-01-14T21:13:37.000Z","updated_at":"2025-04-02T10:42:10.000Z","dependencies_parsed_at":"2022-08-22T04:41:01.489Z","dependency_job_id":null,"html_url":"https://github.com/Breta01/handwriting-ocr","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/Breta01%2Fhandwriting-ocr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Breta01%2Fhandwriting-ocr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Breta01%2Fhandwriting-ocr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Breta01%2Fhandwriting-ocr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Breta01","download_url":"https://codeload.github.com/Breta01/handwriting-ocr/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248625443,"owners_count":21135512,"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":["handwriting-ocr","machine-learning","ocr","opencv","python","recognition","tensorflow"],"created_at":"2024-09-24T20:49:11.435Z","updated_at":"2025-04-12T19:42:54.349Z","avatar_url":"https://github.com/Breta01.png","language":"Jupyter Notebook","readme":"# Handwriting OCR\nThe project tries to create software for recognition of a handwritten text from photos (also for Czech language). It uses computer vision and machine learning. And it experiments with different approaches to the problem. It started as a school project which I got a chance to present on Intel ISEF 2018.\n\n\u003cp align=\"center\"\u003e\u003cimg src =\"doc/imgs/poster.png?raw=true\" height=\"340\" alt=\"Sublime's custom image\" /\u003e\u003c/p\u003e\n\n## Program Structure\nProces of recognition is divided into 4 steps. The initial input is a photo of page with text.\n\n1. Detection of page and removal of background\n2. Detection and separation of words\n3. Normalization of words\n4. Separation and recognition of characters (recognition of words)\n\nMain files combining all the steps are [OCR.ipynb](notebooks/OCR.ipynb) or [OCR-Evaluator.ipynb](notebooks/ocr_evaluator.ipynb). Naming of files goes by step representing - name of machine learning model.\n\n## Getting Started\n### 1. Clone the repository\n```\ngit clone https://github.com/Breta01/handwriting-ocr.git\n```\nAfter downloading the repo, you have to download the datasets and models (for more info look into [data](data/) and [models](models/) folders).\n\n### 2. Requirements\nThe project is created using Python 3.6 with Jupyter Notebook. I recommend using Anaconda. If you have it, you can run the installation as:\n```\nconda create --name ocr-env --file environment.yml\nconda activate ocr-env\n```\nMain libraries (all required libraries are in [environment.yml](environment.yml)):\n* Numpy (1.13)\n* Tensorflow (1.4)\n* OpenCV (3.1)\n* Pandas (0.21)\n* Matplotlib (2.1)\n\n### Run\nWith all required libraries installed and cloned repo, run `jupyter notebook` in the directory of the project. Then you can work on the particular notebook.\n\n## Contributing\nBest way how to get involved is through creating [GitHub issues](https://github.com/Breta01/handwriting-ocr/issues) or solving one! If there aren't any issues you can contact me directly on email.\n\n## License\n**MIT**\n\n## Support the project\nIf this project helped you or you want to support quick answers to questions and issues. Or you just think it is an interesting project. Please consider a small donation.\n\n[![paypal](https://www.paypalobjects.com/en_US/i/btn/btn_donate_LG.gif)](https://paypal.me/bretahajek/2)\n","funding_links":["https://github.com/sponsors/Breta01","https://paypal.me/bretahajek/20","https://paypal.me/bretahajek/2"],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbreta01%2Fhandwriting-ocr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbreta01%2Fhandwriting-ocr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbreta01%2Fhandwriting-ocr/lists"}