Face Recognition Attendance System

Developed a Face Recognition Attendance System using image processing and deep learning techniques.

The project focused on improving face recognition accuracy through image enhancement techniques, including Median Filtering, Contrast Stretching, Histogram Equalization, High-Boost Filtering, and Gamma Correction.

A Convolutional Neural Network (CNN) was then trained to recognize and classify faces. The project included data preprocessing, image enhancement, model training, evaluation, and performance optimization.

The optimized model achieved an average accuracy of 96.08%, with the best experiment reaching approximately 97.1% accuracy.

This work was also developed as part of a research paper that was published in IEEE and presented at ICCA 2025.