Face Recognition Based on LBPH Algorithm

Abstract

In this paper, we propose a face detection and recognition system based on computer vision of improving security issues. Here, we propose our research by applying significant experiments to test the performance of machine learning using of Haar-Cascade Classifier for detecting face image. We analyze this classifier algorithm by divided into four steps. In this paper, we have to make extraction of Haar-feature selection, creating integral image, Adaboost training, Cascading Classifiers for complete the detection step. We have used Local Binary Patterns Histograms (LBPH) algorithm to complete facial recognition system. We propose several parameters in LBPH and we obtain a training dataset by applying training algorithm. We complete computational part by applying LBPH operation and extracting the histograms. We use different kinds of law to find the difference between two histogram like as Euclidian distance, chi-square etc.