{"id":28919441,"url":"https://github.com/jeslipriya/emotion-detection","last_synced_at":"2025-07-03T13:33:06.143Z","repository":{"id":300497633,"uuid":"1006320582","full_name":"jeslipriya/EMOTION-DETECTION","owner":"jeslipriya","description":"This project is an enhanced real-time facial emotion detection system that uses deep learning (OpenCV + mini-XCEPTION) to accurately recognize human emotions through a webcam or image input. It features advanced preprocessing, temporal smoothing, and a clean visual interface for smooth and stable emotion analysis.","archived":false,"fork":false,"pushed_at":"2025-06-30T15:18:28.000Z","size":5746,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-30T15:46:12.232Z","etag":null,"topics":["7-emotions","deep-learning","emotion-detection","fer2013","numpy","opencv","opencv-python","python","tensorflow"],"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/jeslipriya.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,"zenodo":null}},"created_at":"2025-06-22T01:58:10.000Z","updated_at":"2025-06-30T15:23:03.000Z","dependencies_parsed_at":null,"dependency_job_id":"8e874226-9b5c-4a54-89de-f1f31804f744","html_url":"https://github.com/jeslipriya/EMOTION-DETECTION","commit_stats":null,"previous_names":["jeslipriya/emotion-detection"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jeslipriya/EMOTION-DETECTION","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeslipriya%2FEMOTION-DETECTION","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeslipriya%2FEMOTION-DETECTION/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeslipriya%2FEMOTION-DETECTION/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeslipriya%2FEMOTION-DETECTION/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jeslipriya","download_url":"https://codeload.github.com/jeslipriya/EMOTION-DETECTION/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeslipriya%2FEMOTION-DETECTION/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263335502,"owners_count":23450862,"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":["7-emotions","deep-learning","emotion-detection","fer2013","numpy","opencv","opencv-python","python","tensorflow"],"created_at":"2025-06-22T03:30:48.444Z","updated_at":"2025-07-03T13:33:06.135Z","avatar_url":"https://github.com/jeslipriya.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Enhanced Real-Time Emotion Detection System\n\n## Overview\n\nThis project presents an advanced real-time facial emotion detection system leveraging OpenCV's deep learning-based face detection and a pre-trained mini-XCEPTION model trained on the FER2013 dataset. It is designed to provide high-accuracy emotion recognition with enhanced preprocessing, confidence-based visualization, and temporal smoothing for more stable predictions.\n\n---\n\n## Features\n\n* 🚀 **Real-Time Emotion Detection** via webcam\n* 💡 **Accurate Face Detection** using OpenCV DNN (Caffe SSD)\n* 🎭 **Emotion Classification** using mini-XCEPTION (FER2013)\n* 📊 **Dynamic FPS Counter** for performance feedback\n* 🎨 **Color-Coded Emotion Visualization** for clarity\n* ⚖️ **Temporal Prediction Smoothing** using weighted history\n* 🌐 **Emotion Confidence Chart** for real-time analytics\n* 💧 **Enhanced Preprocessing** using CLAHE, Gaussian Blur, Histogram Equalization\n\n---\n\n## Emotion Categories\n\n* Angry\n* Disgust\n* Fear\n* Happy\n* Sad\n* Surprise\n* Neutral\n\n---\n\n## Requirements\n\nInstall the necessary dependencies:\n\n```bash\npip install opencv-python numpy keras tensorflow\n```\n\nEnsure the following pre-trained models are downloaded and placed in the same directory:\n\n| File Name                                  | Description               | Download Source                                                                                                                              |\n| ------------------------------------------ | ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |\n| `deploy.prototxt`                          | Face detector config      | [Link](https://github.com/opencv/opencv/blob/master/samples/dnn/face_detector/deploy.prototxt)                                               |\n| `res10_300x300_ssd_iter_140000.caffemodel` | Face detector weights     | [Link](https://github.com/opencv/opencv_3rdparty/blob/dnn_samples_face_detector_20180205_fp16/res10_300x300_ssd_iter_140000_fp16.caffemodel) |\n| `fer2013_mini_XCEPTION.102-0.66.hdf5`      | Pre-trained emotion model | [Link](https://github.com/oarriaga/face_classification)                                                                                      |\n\n---\n\n## How to Run\n\n```bash\npython your_script_name.py\n```\n\n* The webcam feed will start.\n* Make facial expressions such as happy 😄, angry 😡, sad 😞.\n* Press `Q` to quit the application.\n\n---\n\n## Output Display\n\n* Detected faces with colored bounding boxes based on predicted emotion\n* Emotion labels with confidence percentages\n* Emotion confidence bar chart for the primary face\n* FPS counter and quit instructions\n\n---\n\n## Technical Enhancements\n\n* **Face Detection**: Uses OpenCV DNN with Caffe SSD for fast and accurate detection\n* **Image Preprocessing**: Combines CLAHE, histogram equalization, and Gaussian blur for improved model input quality\n* **Temporal Smoothing**: A deque-based weighted history buffer stabilizes real-time predictions\n* **Visualization**: Live emotion probability bar chart and dynamic label rendering improve usability and feedback\n\n---\n\n## Applications\n\n* Human-computer interaction\n* Real-time feedback systems\n* Affective computing\n* Educational or training tools for emotional intelligence\n\n---\n\n## Credits\n\nDeveloped by Jesli, inspired by the open-source contributions from the computer vision and AI community. Special thanks to the authors of the FER2013 dataset and the mini-XCEPTION model.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjeslipriya%2Femotion-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjeslipriya%2Femotion-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjeslipriya%2Femotion-detection/lists"}