An enhancement of haar cascade algorithm applied to face recognition for gatepass security

ABSTRACT: This study is focused on enhancing the Haar Cascade algorithm to decrease the false positive and false negative rate in face matching, improve face detection accuracy and detect real human faces even under challenging conditions. The face recognition library from OpenCV was implemented with Haar Cascade where 128-dimensional vectors representing the unique features of a face were encoded. A subprocess was applied where the grayscale image from the Haar Cascade was converted to RGB to improve the face encoding. Logical process and filtering were used to decrease non-face detection. The Enhanced Haar Cascade Algorithm produced a 98.39% accuracy rate, 63.59% precision rate, 98.30% recall rate, and 72.23% in F1 Score. The original and enhanced algorithms used the Confusion Matrix Test with 301,950 comparison 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. Face matching and face detection are more accurate in images with complex backgrounds, lighting variations, and occlusions, or even those with similar attributes.

Filipiniana