{"id":25228280,"url":"https://github.com/asherk7/ethnivision","last_synced_at":"2026-04-15T05:31:37.842Z","repository":{"id":192328677,"uuid":"668907175","full_name":"asherk7/ethnivision","owner":"asherk7","description":"Utilizing neural networks to predict ethnicity, age, and gender through images","archived":false,"fork":false,"pushed_at":"2023-09-03T03:53:02.000Z","size":162537,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-30T02:28:00.077Z","etag":null,"topics":["docker","machine-learning","ml","mongodb","neural-network","nodejs","reactjs","swe","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","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/asherk7.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}},"created_at":"2023-07-20T22:06:56.000Z","updated_at":"2025-06-05T21:38:24.000Z","dependencies_parsed_at":"2023-09-04T08:01:02.247Z","dependency_job_id":null,"html_url":"https://github.com/asherk7/ethnivision","commit_stats":null,"previous_names":["asherk7/ethnivision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/asherk7/ethnivision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fethnivision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fethnivision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fethnivision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fethnivision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/asherk7","download_url":"https://codeload.github.com/asherk7/ethnivision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/asherk7%2Fethnivision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31828530,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T18:05:02.291Z","status":"online","status_checked_at":"2026-04-15T02:00:06.175Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["docker","machine-learning","ml","mongodb","neural-network","nodejs","reactjs","swe","tensorflow"],"created_at":"2025-02-11T09:52:35.623Z","updated_at":"2026-04-15T05:31:37.818Z","avatar_url":"https://github.com/asherk7.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EthniVision\n* EthniVision is a website created using React and Express that takes in an image of the user and returns their predicted ethnicity, age, and gender.  \n* It utilizes a machine learning model created using the FairFace dataset.  \n* Created using Docker, Tensorflow, Keras, pandas, Numpy, React, Express, Node.js, and MongoDB.\n\n# Prerequisites  \n* This project was built and ran entirely using docker, so to use this project you will need to have docker installed on your machine.  \n* Docker provides a self-contained environment, ensuring that all the necessary dependencies, libraries, and configurations are encapsulated within the Docker containers.\n\n# Installing\nYou can find the installation instructions for docker [here](https://docs.docker.com/get-docker/).  \nVerify the installation by running the following command in your terminal:  \n```\ndocker --version\n``` \nInstall the project by cloning the repository:  \n```\ngit clone git@github.com:asherk7/EthniVision.git\n```\n\n# Running the program\nMake sure you have docker installed and running.  \nIn the root directory of the project, run the following command:  \n```\ndocker-compose up --build\n```\nThis will build the docker images and run the containers.  \nThe website will be available at http://localhost:3000/  \nTo stop the program, run the following command:  \n```\ndocker-compose down\n```\nTo remove the docker images, run the following command:  \n```\ndocker rmi \u003cimage_name\u003e\n```\n\n# Machine Learning Process\n* The neural network was created using Tensorflow and Keras.\n* The dataset contained over 100,000 images, which was split into a train, val, and test set.\n* the entire machine learning process is documented and can be found in the [machine_learning](https://github.com/asherk7/EthniVision/blob/main/ml/ethnivision_model_building.ipynb) notebook.\n* The model utilized multiclass-multioutput classification by predicting between 9 age categories, 2 gender categories, and 6 ethnicity categories.\n* The model achieved 56% accuracy for age, 87% accuracy for gender, and 72% accuracy for ethnicity on the test set.\n* The model was then saved and incorporated into the backend, where it is used to make predictions on the user's image sent from the frontend.\n\n# References  \n* The dataset I used was the FairFace face image dataset. It contains 108,501 race-balanced images from 7 different race groups: White, Black, Indian, East Asian, Southeast Asian, Middle Eastern, and Latino.  \n* The data was sourced from the [FairFace Github Repository](https://github.com/dchen236/FairFace)  \n\n# Citation\nKarkkainen, Kimmo and Joo, Jungseock. (2021). FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 1548-1558. 10.1109/WACV48630.2021.00159","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasherk7%2Fethnivision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fasherk7%2Fethnivision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fasherk7%2Fethnivision/lists"}