{"id":20906001,"url":"https://github.com/canxkoz/multiple-face-recognition","last_synced_at":"2025-05-13T05:31:24.277Z","repository":{"id":84692760,"uuid":"183842321","full_name":"canxkoz/Multiple-Face-Recognition","owner":"canxkoz","description":"Multipe Face Recognition program that uses Keras and OpenCV. ","archived":false,"fork":false,"pushed_at":"2019-06-04T20:40:40.000Z","size":6063,"stargazers_count":15,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-01T18:50:13.653Z","etag":null,"topics":["face","face-detection","face-recognition","multiple-faces"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/canxkoz.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":"2019-04-28T02:07:49.000Z","updated_at":"2024-06-05T07:23:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"c0b1be03-4865-4d7c-a14f-a2a713d26314","html_url":"https://github.com/canxkoz/Multiple-Face-Recognition","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/canxkoz%2FMultiple-Face-Recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/canxkoz%2FMultiple-Face-Recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/canxkoz%2FMultiple-Face-Recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/canxkoz%2FMultiple-Face-Recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/canxkoz","download_url":"https://codeload.github.com/canxkoz/Multiple-Face-Recognition/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253882995,"owners_count":21978585,"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":["face","face-detection","face-recognition","multiple-faces"],"created_at":"2024-11-18T13:28:36.370Z","updated_at":"2025-05-13T05:31:24.272Z","avatar_url":"https://github.com/canxkoz.png","language":"Python","readme":"# Multiple-Face-Recognition\n\nMultipe Face Recognition program that uses Keras and OpenCV. I built this as a part of DVCHacks.\n\n![Testing Image](pictures_for_readme/Test.jpg)\n\n## build_dataset.py\n\nTaking pictures of the user by using OpenCV. Saving those pictures in a folder named \"dataset\". By the use of haarcascade features the pictures only include human faces.\n\n![Creating a Dataset](pictures_for_readme/Build_Dataset.JPG)\n\n## train_data.py\n\nI created a convolutional feature extractor network with multiple layers. I did that in order to genereate a representation vector of the input images which will make use of \"dataset\". \n- Softmax is used in this project as a last layer. output activation function. \n- The training is done by the use of the Adam optimizer function. \n- The learning rate of the Adam optimizer is 3e-4. \n- As a loss function I used binary crossentropy, the reason why I preferred binary crossentopy is becasue there were two classes. \n- For future work if you want to add more classes you may use categorical crossentropy function. \n- The validation set is chosen as 10% of the training set.\n- The traninig of my model is complteted within 30 epochs. \n- Validation accuracy, validation loss of the model is printed at the end of the training process. \n- At last weights are saved as a \".h5\" file and model structure is saved as a \".yaml\" file and both of them are kept in \"keras_model\" folder.  \n\n![Training the Model](pictures_for_readme/Train_Data.JPG)\n\n## check_result.py\n\nThe test accuracy can be seen from the results of this file. In this file, I crate labels for the test set.\n\n![Creating a Dataset](pictures_for_readme/Check_Result.JPG)\n\n## real_time_re.py\n\nReal time test of the model from the webcam of your setup.\n\nReferences\n- [Keras](https://keras.io/)\n- [OpenCV](https://opencv.org/)\n- [TensorFlow](https://www.tensorflow.org/)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcanxkoz%2Fmultiple-face-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcanxkoz%2Fmultiple-face-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcanxkoz%2Fmultiple-face-recognition/lists"}