{"id":26120899,"url":"https://github.com/prudhvideep/video-face-recognition","last_synced_at":"2026-04-04T08:38:43.583Z","repository":{"id":246117547,"uuid":"820149322","full_name":"prudhvideep/Video-Face-Recognition","owner":"prudhvideep","description":"An application to detect faces in video streams, seamlessly adjusting to varying workloads. It's designed for both small-scale and large-scale, high-performance deployments.","archived":false,"fork":false,"pushed_at":"2025-01-14T06:17:22.000Z","size":31534,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-14T07:26:15.388Z","etag":null,"topics":["aws","docker","python-lambda","python3","reactjs","tailwindcss","terraform"],"latest_commit_sha":null,"homepage":"https://main.d2g4ycz7ogc8gz.amplifyapp.com/","language":"JavaScript","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/prudhvideep.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":"2024-06-25T22:49:04.000Z","updated_at":"2025-01-14T06:17:25.000Z","dependencies_parsed_at":"2024-06-25T23:50:45.556Z","dependency_job_id":"38ea0d8e-2956-4f3c-9adc-f8591f5d4e41","html_url":"https://github.com/prudhvideep/Video-Face-Recognition","commit_stats":null,"previous_names":["prudhvideep/video-face-recognition"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prudhvideep%2FVideo-Face-Recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prudhvideep%2FVideo-Face-Recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prudhvideep%2FVideo-Face-Recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prudhvideep%2FVideo-Face-Recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/prudhvideep","download_url":"https://codeload.github.com/prudhvideep/Video-Face-Recognition/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242864302,"owners_count":20197689,"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":["aws","docker","python-lambda","python3","reactjs","tailwindcss","terraform"],"created_at":"2025-03-10T13:53:06.858Z","updated_at":"2025-12-30T19:34:41.985Z","avatar_url":"https://github.com/prudhvideep.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Video Face Recognition\n\nIn this project, I built an elastic application that can scale out on-demand and detect faces present in a video. I built this using the PaaS offerings from AWS - specifically AWS Lambda and other supporting services from AWS.\n\n\u003cdiv style=\"text-align: center;\"\u003e\n    \u003cimg src=\"./public/images/demo.gif\" alt=\"Demo\"\u003e\n\u003c/div\u003e\n\n**Try it here :**  https://main.d2g4ycz7ogc8gz.amplifyapp.com/\n\n## Components\n\nIn this section, I'll describe the main components of this application.\n\n### Frontend\n\nThe front end is built using **React.js** and styled with **TailwindCss**, ensuring a responsive design. The application is secured with **Firebase Authentication**.\n\u003c!-- \u003cp align=\"center\"\u003e\n  \u003cimg src=\"./public/images/Responsive Website.png\" alt=\"Dashboard\" width=\"100%\" height=\"auto\" style=\"max-height: 300px; object-fit: contain;\"/\u003e\n\u003c/p\u003e --\u003e\n\n\u003c!-- \u003cp align=\"center\"\u003e\n  \u003cimg src=\"./public/images/Dashboard.jpeg\" alt=\"Dashboard\" width=\"50%\" height=\"auto\" style=\"max-height: 300px; object-fit: contain;\"/\u003e\n\u003c/p\u003e --\u003e\n\n### Backend\n\nOur video analysis application uses four Lambda functions to implement a multi-stage pipeline to process videos sent by users.\n\n- The pipeline starts with a user uploading a video to the input bucket (through the web interface).\n- ***video-splitting function*** splits the video into frames and chunks them into the group-of-pictures (GoP) using FFmpeg. It stores this group of pictures in an intermediate stage-1 bucket.\n- ***face-recognition function*** extracts the faces in the pictures using a Single Shot MultiBox Detector (SSD) algorithm and uses only the frames with faces for face recognition. It uses a pre-trained CNN model (ResNet-34) for face recognition and outputs the name of the extracted face. The final output is stored in the output bucket.\n\nThe structure of the application is shown in the figure below. I used AWS Lambda for serverless computation and S3 for storing the data required for the functions.\n\n\u003e [!IMPORTANT]\n\u003e\n\u003e The demo only accepts video files and the file size is capped to 5mb to stay within the free tier limits.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./public/images/architecture-diagram.png\" alt=\"architecture-diagram\" width=\"auto\" height=\"auto\" style=\"max-height: 300px; object-fit: contain;\"/\u003e\n\u003c/p\u003e\n\n## Setup\n\n### Clone the repository\n\n```\ngit clone git@github.com:prudhvideep/Video-Face-Recognition.git \u0026\u0026 cd Video-Face-Recognition/\n```\n\n### Prerequisites\n\n- Terraform CLI (1.2.0+)\n- Aws CLI installed.\n- npm\n- AWS account and associated credentials.\n\n### Initialize Infrastructure\n\nExecute the script **setup_infrastructure.sh** to install all the prerequisites and initialize the infrastructure in AWS (***using terraform*** )\n\n```\nchmod +X ./scripts/setup_infrastructure.sh \u0026\u0026 sh ./scripts/setup_infrastructure.sh\n```\n\nEnter your *aws_access_key_id* and *aws_secret_access_key* when prompted\n\n```\npmutyal@Prudhvi:~/video-face-recognition$ ./scripts/setup_infrastructure.sh \n\nChecking and installing prerequisites...\nTerraform is already installed.\nAWS CLI is already installed.\nDocker is already installed.\nnpm is already installed.\nAll prerequisites are installed.\n\nSetting AWS credentials...\nEnter your AWS Access Key ID: \u003cYOUR_ACCESS_KEY\u003e\nEnter your AWS Secret Access Key: \u003cYOUR_SECRET_KEY\u003e\n```\n\n\n\nThis script initializes the infrastructure and outputs the necessary lambda function urls.\n\u003cbr\u003e\n\u003cbr\u003e\nTo teardown the infrastructure, execute\n\n```\nchmod +X ./scripts/destroy_infrastructure.sh \u0026\u0026 sh ./scripts/destroy_infrastructure.sh\n```\n\n### Firebase\n\nCreate a Firebase project, set the authentication with email, and add the Gmail provider to implement sign-in with Gmail.\n\n- **References**: please refer this article [Firebase Authentication](https://medium.com/@Adekola_Olawale/firebase-authentication-413626c5234d).\n\n### Environment Variables\n\nsetup a .env file\n```\ntouch .env\n```\nUpdate the following environment variables\n\n```\n#firebase keys\nREACT_APP_FIREBASE_API_KEY =\"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_AUTH_DOMAIN = \"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_PROJECT_ID = \"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_STORAGE_BUCKET = \"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_MESSAGING_SENDER_ID = \"\u003c\u003cYour Key\u003e\u003e\"\n\n#Aws keys\nREACT_APP_S3_BUCKET_INPUT = \"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_S3_BUCKET_OUTPUT = \"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_PRESIGNED_LAMBDA_URL = \"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_OUTPUT_LAMBDA_URL = \"\u003c\u003cYour Key\u003e\u003e\"\nREACT_APP_DELETE_LAMBDA_URL = \"\u003c\u003cYour Key\u003e\u003e\"\n```\n\n### Start React Application\nInstall the project dependencies by running:\n\n```\nnpm install\n```\n\nStart the development server\n\n```\nnpm start\n```\nTo build the production application, run the following:\n\n```\nnpm run build\n```\n\n### Upcoming Features\n\n- Standard Logging.\n- Support for multiple media types.\n- Detecting videos with multiple characters.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprudhvideep%2Fvideo-face-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprudhvideep%2Fvideo-face-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprudhvideep%2Fvideo-face-recognition/lists"}