Abstract

Human face plays an important role in our social interaction, conveying people’s identity but it is a dynamic object and has a high degree of variability in its appearences. Face recognition is one of the most popular applications of image analysis. In present scenario, face recognition plays a major role in security, personal information accesses, improved human machine interaction and personalized advertising. Recently, technology became available to allow verification of “true” individual identity. This technology is based in a field called “biometrics”. Biometric access control are automated methods of verifying or recognizing the identity of a living person on the basis of some physiological characteristics, such as fingerprints or facial features, or some aspects of the person’s behavior, like his/her handwriting style or keystroke patterns. The aim of this study is to design a facial recognition algorithm using SVM classifier. The process begins by reading images into the model and the image features were extracted by converting to gray scale the to LBP values which carries labeled components. The detector model called face cascade classifier is used to capture facial region and positions. The detected faces are matched and trained with the SVM model for recognition. The implementation was carried out using Pycharm-studio 2019 for python programming language with machine learning tools. It can be concluded that the accuracy of the machine learning detecting model is profoundly reliant on the idea of image face dataset got for testing and training the algorithms. The model may fail to detect face in the image if it is tilted by some angle then it cannot detect the face because the researcher considers the image height and width during certain calculation like merging, overlapping. Current algorithm needs some efforts in detecting various pose from images base on emotional status. Also, experiments should be carried out to observe and analyze different kernels for classification using Support Vector Machine.