{"id":15937935,"url":"https://github.com/reuseman/captchify","last_synced_at":"2026-04-17T12:33:45.977Z","repository":{"id":134301048,"uuid":"227705372","full_name":"reuseman/Captchify","owner":"reuseman","description":"✳️ Python application for automatic Captcha recognition. Implemented using TensorFlow to create neural networks models and support vector machines. Equipped with a graphical and command line interface.","archived":false,"fork":false,"pushed_at":"2019-12-13T16:59:27.000Z","size":56730,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-31T23:15:24.184Z","etag":null,"topics":["captcha","captcha-solver","gui","machine-learning","python3","qt5","tensorflow","university-project"],"latest_commit_sha":null,"homepage":"https://gitlab.com/reuseman/captcha-solver","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/reuseman.png","metadata":{"files":{"readme":"README.MD","changelog":"history/1/binarized/aaam.jpg","contributing":null,"funding":null,"license":null,"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":"2019-12-12T22:07:23.000Z","updated_at":"2022-02-26T21:33:11.000Z","dependencies_parsed_at":null,"dependency_job_id":"b992eea5-53b2-4efc-bc5c-28a1370b1d6a","html_url":"https://github.com/reuseman/Captchify","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/reuseman/Captchify","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reuseman%2FCaptchify","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reuseman%2FCaptchify/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reuseman%2FCaptchify/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reuseman%2FCaptchify/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reuseman","download_url":"https://codeload.github.com/reuseman/Captchify/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reuseman%2FCaptchify/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262963652,"owners_count":23391867,"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":["captcha","captcha-solver","gui","machine-learning","python3","qt5","tensorflow","university-project"],"created_at":"2024-10-07T05:20:22.931Z","updated_at":"2026-04-17T12:33:40.936Z","avatar_url":"https://github.com/reuseman.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# About the project\nThis project was made by me and [Mario Parisi](https://gitlab.com/MaggioFG) for a university exam. More in the specific was for a Pattern Recognition exam. For others info and a complete documentation check [Captcha solver.pdf](https://github.com/reuseman/Captchify/blob/master/Captcha%20solver.pdf)\n\n----\n\nMirror of the repository:\nhttps://gitlab.com/reuseman/captcha-solver\n\n\nThe project used the version of python 3.6 and the current libraries:\n\nmatplotlib==3.0.2\nscikit_image==0.14.2\ntensorflow_gpu==1.12.0\nnumpy==1.13.3\njoblib==0.13.1\nscipy==1.2.0\nKeras==2.2.4\nPyQt5==5.12\nskimage==0.0\nscikit_learn==0.20.2\ntensorflow==1.12.0\n\nTo give a brief overview on how to use this code, a description of how to use \nthe main files is provided.\n\nmain_gui.py\nStarts the qt5 gui, the model of ML can be choosed and then used to predict the\ncaptcha. The model cannot be trained currently, and it will be improved in \nfuture version. The input can be an image and the solution will be written on the GUI.\nOtherwise a folder can be selected and the solution will be written as the name \nof the files.\n\nmain_cli.py\nStarts a cli that provides different operation that are quite sequential.\nIndeed, the first operation is to split the dataset into train, test and evaluation set that will be used for the rest of operations.\nThe second operation is train model that asks for different parameters and then saves the model.\nIndeed, the first operation is to split the dataset into train, test and evaluation\nset that will be used for the rest of operations.\nThe second operation is train model that asks for different parameters and then\nsaves the model.\nThen evaluate model provides the accuracy of the latest model on a specific set.\nWhile kfold validation uses the kfold method to do the evaluation on all the dataset.\nAnd finally solve captcha asks for a path of an image or a folder and will provide the solution.\nThe path can be absolute like /home/john/project/dataset/original or relative dataset/original if the current working directory is /home/john/project\nAnd finally solve captcha asks for a path of an image or a folder and will \nprovide the solution.\nThe path can be absolute like /home/john/project/dataset/original or \nrelative dataset/original if the current working directory is /home/john/project\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freuseman%2Fcaptchify","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freuseman%2Fcaptchify","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freuseman%2Fcaptchify/lists"}