Profile Face Recognition Using Local Binary Patterns with Artificial Neural Network

Abstract

Face recognition is a process of identifying a person based on facial features. It is one of the most popular and widely used biometrics technique today. However, there are challenges regarding robust, rotation-invariant, real-time face recognition systems. Few challenges can be listed as changes in illumination, rotations of the face, different head poses and occlusion etc. This study mainly consists of four parts, namely face detection from the image, feature extraction, training the neural network and recognition. Face detection algorithm is used to detect the face from the given image. The most useful and unique features of the face image are extracted in the feature extraction phase. The face area is first divided into K<inf>2</inf> sub regions from which Local Binary Pattern (LBP) histograms are extracted and concatenated into a single feature vector which is used to train the Neural Network. In the recognition phase, face recognition is done by trained Neural Network. The system is trained and tested on Ondokuz Mayis University database. © 2018 IEEE.