oarriaga/face_classification
Face Classification
This project is a deep learning face classification system that detects human faces and classifies gender and emotion. It utilizes convolutional neural networks and computer vision tools to analyze facial attributes in both static images and live video streams.
The system includes specialized classifiers for emotions based on the FER2013 dataset and gender based on IMDB datasets. These models are integrated into a containerized web service, allowing the classification logic to be exposed as an API that processes image data via network requests.
The technical surface covers the entire pipeline from custom model training with Keras to real-time face detection using OpenCV. This includes the implementation of a video pipeline for continuous frame processing and the use of Haar cascades for locating faces.
Features
- Emotion Classifiers - Classifies human emotions and gender from images and live video using deep learning networks.
- Face Detection - Identifies human faces within live video streams to prepare data for downstream attribute analysis.
- Custom Model Training - Implements custom training pipelines using Keras to create gender and emotion classification models from labeled image datasets.
- Attribute Classifiers - Combines face detection with Keras-based CNNs to classify gender and emotion.
- Facial Emotion Classifiers - Provides a vision tool that identifies human emotions based on the FER2013 dataset.
- Facial Expression Recognition - Analyzes facial muscle patterns to categorize emotional states and gender using trained neural networks.
- Gender Predictions - Implements a neural network trained on IMDB datasets to predict the gender of subjects in photographs.
- CNN Architectures - Implements convolutional neural network architectures to extract visual patterns for gender and emotion classification.
- Computer Vision - Implements computer vision capabilities for facial recognition and classification deployed as a web service.
- Keras Model Implementations - Utilizes the Keras API to implement and train deep learning architectures for facial attribute classification.
- Cascade Classifier Detections - Uses OpenCV Haar cascade classifiers to locate human faces by scanning for edge and line patterns.
- Real-Time Facial Recognition - Performs low-latency identification of emotions and gender from live video streams.
- Face Recognition and Analysis - Detects human faces and analyzes associated attributes like gender and emotion within image frames.
- Real-Time Model Inference on Frames - Implements a high-speed video pipeline that runs model inference on every frame of a live camera stream.
- Model Training Implementations - Implements the training of custom classification models for gender and emotion using Keras and labeled datasets.
- Image Classification APIs - Ships a RESTful API that accepts image data and returns classification results for facial attributes.
- Containerized Service Deployments - Packages the classification service within containers to ensure consistent deployment and inference across environments.
- Inference APIs - Exposes the facial analysis model as a web service that accepts image data and returns classification results.
- Age gender estimation - Listed in the “Age gender estimation” section of the Ailia Models awesome list.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
