{"id":15698878,"url":"https://github.com/checktor/face_amnesia","last_synced_at":"2025-05-05T21:11:40.250Z","repository":{"id":38023012,"uuid":"183596605","full_name":"checktor/face_amnesia","owner":"checktor","description":"Face detection and retrieval in image and video files.","archived":false,"fork":false,"pushed_at":"2025-01-02T20:29:49.000Z","size":106541,"stargazers_count":7,"open_issues_count":10,"forks_count":2,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-05-05T21:11:27.899Z","etag":null,"topics":["clustering","deduplication","face-detection","face-recognition","image-processing","locality-sensitive-hashing","nearest-neighbors","video-processing"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/checktor.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":"2019-04-26T09:09:38.000Z","updated_at":"2025-01-02T20:29:31.000Z","dependencies_parsed_at":"2024-10-24T05:41:04.708Z","dependency_job_id":null,"html_url":"https://github.com/checktor/face_amnesia","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/checktor%2Fface_amnesia","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/checktor%2Fface_amnesia/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/checktor%2Fface_amnesia/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/checktor%2Fface_amnesia/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/checktor","download_url":"https://codeload.github.com/checktor/face_amnesia/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252577020,"owners_count":21770721,"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":["clustering","deduplication","face-detection","face-recognition","image-processing","locality-sensitive-hashing","nearest-neighbors","video-processing"],"created_at":"2024-10-03T19:35:24.879Z","updated_at":"2025-05-05T21:11:40.245Z","avatar_url":"https://github.com/checktor.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# face_amnesia\nDetect and retrieve the face of a specific person in image and video files using pre-trained models.\n\n## Requirements\n\n### Language\n* Python (\u003e= 3.5)\n\n### Dependencies\n* NumPy (http://www.numpy.org/)\n    * basic numerical computations\n* scikit-learn (https://scikit-learn.org/stable/)\n    * PCA\n* OpenCV (https://opencv.org/)\n    * basic image and video processing\n* dlib (http://dlib.net/)\n    * face detection and recognition models\n\n## Install\n\n### Use pre-compiled libraries\nRun provided [install script](install.sh) to use pre-compiled versions\nof OpenCV and dlib (without GPU support) available via pip. Note that\ncorresponding pre-built OpenCV package is unofficial but works\nfine. See comments in install script for further details.\n\n### Use Dockerfile\nRun provided [Dockerfile](Dockerfile) to compile OpenCV and dlib by hand\nusing the official Ubuntu 20.04 image.\n    \n    cd /path/to/face_amnesia/\n    docker build -t face_amnesia .\n    docker run -it face_amnesia\n\nNote that it is possible to enable hardware-dependent optimization such\nas AVX instructions or CUDA support. See comments in Dockerfile for\nfurther details.\n\n## Testing\nRun provided [test script](test.sh) to execute unit and integration tests.\n\n## Usage\nCommand-line interfaces for data point creation and retrieval available\nin project's root directory. Data points and corresponding source\nfiles are stored in and served from a separate `face amnesia` folder\nin current user's home directory which may be identical to project's\nroot directory.\n\n### Data point creation\nCreate face description vectors from media file (image, video) or whole\ndirectory.\n\n    python3 create.py /path/to/media/file/or/directory/\n    \nAvailable options:\n    \n    python3 create.py --help\n\n### Data point retrieval\nRetrieve previously stored data points corresponding to faces similar\nto given one.\n\n    python3 retrieve.py /path/to/query/media/file/\n    \nAvailable options:\n    \n    python3 retrieve.py --help\n\n## Further reading\n* Mayur Datar, Nicole Immorlica, et. al.: \"Locality-Sensitive Hashing Scheme Based on p-Stable Distributions\" (2004)\n* Chris Biemann: \"Chinese Whispers - an Efficient Graph Clustering Algorithm and its Application to Natural Language Processing Problems\" (2006)\n\n## Further tools\n* Adam Geitgey: face_recognition (https://github.com/ageitgey/face_recognition)\n\n## Troubleshooting\nCompiling dlib by hand is usually straightforward. Building OpenCV from\nsource, however, may need some adjustments. The official guides on this\ntopic are useful and can be found on the web:\n\n* http://dlib.net/compile.html\n* https://docs.opencv.org/4.10.0/d7/d9f/tutorial_linux_install.html\n\nThe following paragraphs will provide additional information on\ncompilation problems which may occur on some architectures.\n\n### Compilation: CBLAS / LAPACK headers could not be found  \nPossible workaround:\n\n    sudo cp /usr/include/lapacke*.h /usr/include/openblas/\n    \n### Compilation: GCC version 8 is not supported\nPossible workaround:\n\n    export CC=/path/to/gcc-7/compiler\n\nBuilding dlib's Python bindings with CUDA support needs an additional\nargument to setup.py call:\n    \n    --set CUDA_HOST_COMPILER=/path/to/gcc-7/compiler\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchecktor%2Fface_amnesia","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchecktor%2Fface_amnesia","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchecktor%2Fface_amnesia/lists"}