Facial Recognition System Using Local Binary Patterns(LBP) TS Vishnu Priya, G.Vinitha Sanchez, N.R.Raajan School of Electrical & Electronics Engineering, SASTRA Deemed University, Thanjavur, India tsvpriya1995@gmail.com, gvinithasanchez2592@gmail.com, nrraajan@ece.sastra.edu Abstract - There are several biometrics available like finger print, iris identification etc. But Facial recognition or detection is one of the biometric software applications that can identify an particular individual in an digital image. Face recognitions were used in many applications in the field of banking, passport office etc. But the problem in the face recognition is it cannot identify the person in the case of identical twins. So the algorithm called local binary patters were used to indentify the face in the case of identical twins because the LBP can describe well about the micro patterns present in the face. Key Words - Micro Patterns, Pixels, Local Binary Patterns, Histogram I. INTRODUCTION Facial recognition is considered as a very tough challenge due to variation in size, shape, color, and texture of human faces and also there is no unique method to recognize the face among the humans. Therefore in order to build a fully automated system, a robust and efficient face recognition method is required. The face recognition system consists of recognizing the faces given as input with the data base images[1]. There are several methods available to recognize the face such as appearance based method, support vector machine, hidden Markov model etc. This paper analysis a face recognition based on local binary patterns which is appearance based method. II. EXISTING METHOD In the existing system PCA method is used to recognize the face[4]. Generally, PCA is used for reducing the dimension of the image. But one of the major problem with that is it cannot produce the complete information about the face therefore lose of information may occur in case of PCA algorithm. Also PCA algorithm cannot recognize face in case of identical twins. III. PROPOSED METHOD In order to overcome the above mentioned problems the algorithm local binary pattern is proposed[2]. Since face image is composed of several minute patterns this can be efficiently identified by applying the local binary pattern operator[5]. The local binary pattern operator is applied on the given face image. A. METHOD OF LOCAL BINARY PATTERNS(LBP): In local binary pattern the input face is first converted into the grey image and for that image the binary pattern is calculated by comparing the center pixel with the surrounding pixel. Fig.1. Performance Of Local Binary Pattern (LBP) Operator If the centre pixel is greater than that of the neighboring pixel then it is denoted as 1 and if the neighboring pixel is smaller than that of the centre pixel it is denoted as 0.This should be done for each and every pixel so that we will get the binary pattern. Fig.2. Face image with pixels having uniform and non-uniform patterns The local binary pattern is applied in the input image in order to extract the important features of an image The objective is to calculate the local binary pattern for each and every pixels in an input image. Finally, the histogram is calculated to find out the similarities of an given image. In face recognition systems, the performance of the algorithm is calculated by using the detection and false alarm ratio .The common errors that occur in the face recognition systems are, False Negative: This error will occur because, the face is not exactly recognized due to the poor ratio of detection International Journal of Pure and Applied Mathematics Volume 119 No. 15 2018, 1895-1899 ISSN: 1314-3395 (on-line version) url: http://www.acadpubl.eu/hub/ Special Issue http://www.acadpubl.eu/hub/ 1895