An Enhancement of Haar Cascade Algorithm Applied to Face Recognition for Gate Pass Security

Abstract

This study is focused on enhancing the Haar Cascade algorithm to decrease the false positive and false negative rate of face recognition in images with variations in lighting, facial expressions, and occlusions to increase accuracy. The face recognition library was applied with Haar Cascade where 128-dimensional vectors representing the unique features of a face were encoded. The Enhanced Haar Cascade Algorithm produced a 98.39% accuracy rate, in comparison, the Haar Cascade Algorithm achieved a 46.70% - 77.00% accuracy rate. Both algorithms used the Confusion Matrix Test with 301,950 comparisons using the same dataset of 550 images. The 98.39% accuracy rate shows a significant decrease in false positive and false negative rates in facial recognition in images with complex conditions