{"id":21331420,"url":"https://github.com/tempdata73/face_verification","last_synced_at":"2025-03-16T00:42:44.035Z","repository":{"id":112502605,"uuid":"187273381","full_name":"tempdata73/face_verification","owner":"tempdata73","description":"Real time face tracking and verification","archived":false,"fork":false,"pushed_at":"2020-03-01T00:30:41.000Z","size":67273,"stargazers_count":3,"open_issues_count":4,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-22T13:47:56.670Z","etag":null,"topics":["detection","facenet","tracking","verification"],"latest_commit_sha":null,"homepage":"","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/tempdata73.png","metadata":{"files":{"readme":"README.md","changelog":null,"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":"2019-05-17T19:49:38.000Z","updated_at":"2021-12-15T09:02:16.000Z","dependencies_parsed_at":"2023-03-20T09:01:42.976Z","dependency_job_id":null,"html_url":"https://github.com/tempdata73/face_verification","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tempdata73%2Fface_verification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tempdata73%2Fface_verification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tempdata73%2Fface_verification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tempdata73%2Fface_verification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tempdata73","download_url":"https://codeload.github.com/tempdata73/face_verification/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243809848,"owners_count":20351407,"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":["detection","facenet","tracking","verification"],"created_at":"2024-11-21T22:32:58.811Z","updated_at":"2025-03-16T00:42:44.018Z","avatar_url":"https://github.com/tempdata73.png","language":"Python","readme":"# Real time face tracking and verification\nOpencv-tensorflow-mxnet implementation of face tracking and verification on real time using either CPU or GPU.\nThe pretrained models used for face verification were obtained from [David Sandberg's github repo](https://github.com/davidsandberg/facenet)\nwhich are tensorflow implementations of [FaceNet](https://arxiv.org/abs/1503.03832).\nInstead of using Viola and Jones' face detector, this repository uses a [implementation of the MTCNN model](https://github.com/YYuanAnyVision/mxnet_mtcnn_face_detection) for both face detection and tracking initialization. It is also used for database creation.\n(the original paper can be found [here](https://kpzhang93.github.io/MTCNN_face_detection_alignment/paper/spl.pdf))\n\n## Compatibility\nThe code has been tested using python 3.7.1 under 18.10 Ubuntu.\n\n## Download\n1. Clone this repo and cd to the 'models' directory.\n2. Download either Facenet model from [Sandberg's repo](https://github.com/davidsandberg/facenet).\n3. Run `python prepare_facenet.py path/to/facenet.zip` and cd to parent directory.\n\n## Demo\n1. Cd to the 'src' directory.\n2. Run `python main.py demo/avengers.mp4 demo/user_data.csv demo/embeddings.npy`.\n\n## Guide\nThe program consists of three parts: video file (webcam feed or downloaded video); user metadata and embeddings (both created from the *create_database.py* script). User metadata and embeddings derive from an image folder that contains all of the users to be identified. As a prerequisite you should have both video file and the images folder. Take into account that the image filename of a user will be used as his username.\n1. Cd to the 'src' directory.\n2. Run `python create_database.py output/user_data.csv output/embeddings.npy path/to/images/` to create embedddings.\n3. Run `python main.py video_file.mp4 output/user_data.csv output/embeddings.npy` for face tracking and verification. If you wish to keep track of time a user appears in the video, run *screentime.py* instead of *main.py*.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftempdata73%2Fface_verification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftempdata73%2Fface_verification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftempdata73%2Fface_verification/lists"}