{"id":19878704,"url":"https://github.com/arsath-eng/face_classification","last_synced_at":"2026-05-01T12:33:17.389Z","repository":{"id":248314936,"uuid":"828356405","full_name":"arsath-eng/face_classification","owner":"arsath-eng","description":" a deep learning project that uses ResNet and Inception architectures to classify real vs AI-generated face images. The project includes two models trained on a custom dataset, achieving validation accuracies of 52.45% (ResNet) and 52.94% (Inception). Built with TensorFlow and Flask,  and a web interface for real time face classification","archived":false,"fork":false,"pushed_at":"2024-10-29T11:11:11.000Z","size":1294,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-02T08:44:34.901Z","etag":null,"topics":["ai-detection","computer-vision","deep-learning","face-detection","flask","image-classification","machine-learning","tensorflow"],"latest_commit_sha":null,"homepage":"https://huggingface.co/spaces/arsath-sm/face_classification","language":"Jupyter Notebook","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/arsath-eng.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":"2024-07-13T22:17:51.000Z","updated_at":"2024-10-29T11:11:14.000Z","dependencies_parsed_at":"2024-07-13T23:31:54.280Z","dependency_job_id":"1af88d3d-2ce6-4fb6-99d0-a3323f93d8a2","html_url":"https://github.com/arsath-eng/face_classification","commit_stats":null,"previous_names":["arsath-eng/face_classification"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/arsath-eng/face_classification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arsath-eng%2Fface_classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arsath-eng%2Fface_classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arsath-eng%2Fface_classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arsath-eng%2Fface_classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/arsath-eng","download_url":"https://codeload.github.com/arsath-eng/face_classification/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arsath-eng%2Fface_classification/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32497812,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"online","status_checked_at":"2026-05-01T02:00:05.856Z","response_time":64,"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":["ai-detection","computer-vision","deep-learning","face-detection","flask","image-classification","machine-learning","tensorflow"],"created_at":"2024-11-12T17:06:25.374Z","updated_at":"2026-05-01T12:33:17.346Z","avatar_url":"https://github.com/arsath-eng.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Face Classification Project 🎭\n\n[![Python](https://img.shields.io/badge/Python-3.9-blue.svg)](https://www.python.org)\n[![Flask](https://img.shields.io/badge/Flask-2.1.0-green.svg)](https://flask.palletsprojects.com/)\n[![TensorFlow](https://img.shields.io/badge/TensorFlow-latest-orange.svg)](https://tensorflow.org)\n[![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-Spaces-yellow.svg)](https://huggingface.co/spaces/arsath-sm/face_classification)\n\nA deep learning project for detecting and classifying real and artificially generated face images using ResNet and Inception architectures. 👤✨\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/Banner.png\" alt=\"Project Banner\" width=\"800\"/\u003e\n\u003c/p\u003e\n\n## 📋 Table of Contents\n- [Overview](#overview)\n- [Model Architecture](#model-architecture)\n- [Performance](#performance)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Model Links](#model-links)\n- [Future Improvements](#future-improvements)\n\n## 🔍 Overview\nThis project implements two deep learning models to classify images as either real or AI-generated faces:\n- **Model 1**: ResNet-based architecture with residual connections\n- **Model 2**: Inception-style network with multi-scale feature processing\n\n## 🏗️ Model Architecture\n\n### ResNet Model (Model 1)\n- Deep CNN with residual connections\n- Handles vanishing gradient problem\n- Effective for complex feature learning\n- Multiple residual blocks with increasing filter sizes\n- Dropout layers for regularization\n\n### Inception Model (Model 2)\n- Multi-scale feature processing\n- Efficient computational design\n- Parallel convolutional paths\n- Adaptive to varying face sizes and orientations\n- Better generalization capabilities\n\n## 📊 Performance\n\n| Model | Validation Accuracy | Validation Loss |\n|-------|-------------------|----------------|\n| ResNet | 52.45% | 0.7246 |\n| Inception | 52.94% | 0.6913 |\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/Performance.png\" alt=\"Project Overview\" width=\"600\"/\u003e\n\u003c/p\u003e\n## 🚀 Installation\n\n### 1. Set up Conda Environment\n```bash\n# Create new environment\nconda create -p face python=3.9\n\n# Activate environment\nconda activate face\n\n# Install requirements\npip install -r requirements.txt\n```\n\n### 2. Requirements\nCreate a `requirements.txt` file with:\n```\nFlask==2.1.0\ntensorflow\nnumpy\nopencv-python\npillow\n```\n\n## 💻 Usage\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/output1.png\" alt=\"output\" width=\"600\"/\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/output2.png\" alt=\"output\" width=\"600\"/\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/output3.png\" alt=\"ouput\" width=\"600\"/\u003e\n\u003c/p\u003e\n\n### Running the Flask App\n```bash\npython app.py\n```\nVisit `http://localhost:5000` in your web browser to access the application.\n\n\n## 🔗 Model Links\n\n- [Model 1 on HuggingFace](https://huggingface.co/arsath-sm/face_classification_model1/tree/main)\n- [Model 2 on HuggingFace](https://huggingface.co/arsath-sm/face_classification_model2/tree/main)\n- [Demo Application](https://huggingface.co/spaces/arsath-sm/face_classification)\n- [Flask Application Source](https://github.com/arsath-eng/face_classification.git)\n\n## 🔄 Future Improvements\n\n1. 📈 Data Quality\n   - Investigate dataset biases\n   - Enhance data diversity\n\n2. 🔧 Model Architecture\n   - Experiment with hybrid models\n   - Implement transfer learning\n   - Test ensemble methods\n\n3. ⚡ Performance\n   - Extended training periods\n   - Hyperparameter optimization\n   - Advanced data augmentation techniques\n\n## 🔗 Dataset\n- [dataset about real-fake human face classification](https://drive.google.com/file/d/16y2xEwwuf1v_W0BUDv1thzpNu_dnaJZ1/view?usp=sharing)\n\n## 👥 Contributors\n- Arsath S.M\n- Faahiht K.R.M\n- Arafath M.S.M\n\n## 📄 License\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nThis project is licensed under the [MIT License](LICENSE) - see the [LICENSE](LICENSE) file for details.\n\n---\n\u003cp align=\"center\"\u003e\nMade with ❤️ at University of Jaffna Faculty of Engineering\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farsath-eng%2Fface_classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farsath-eng%2Fface_classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farsath-eng%2Fface_classification/lists"}