Face Recognition with Particle Swarm optimization (PSO) and Support Vector Machine (SVM)

EasyChair Preprint 4807

Abstract

In today's world, face recognition application is still a concerned research area of interest. This is because of the vital role it plays in almost every sectors like security, education, business and so on. it is used in verifying and detecting the correct face in either an image or a video stream. Almost all the algorithms deployed or used in the process of classification problem in face recognition research area, do not guarantee better or optimal performances. Sometimes, optimization becomes necessary even within the selected or desired classification method. In this research, local binary pattern (LBP) was used for feature extraction while support vector machines (SVM) was used as a classifier. However, its important to find good values of hyper parameters c and γ in order to obtain good results. particle swarm optimization (PSO) is proposed to optimize and choose the best SVM hyper parameters. Results obtained using the LBP-PSO-SVM pipeline gave a mean-squared-error of 0.028571 and an overall best accuracy of 98.33%. the proposed framework outperformed the use of SVM alone, with less time of implementation and less complexity.

Keyphrases: Particle Swarm Optimization and, Support Vector Machine, face recognition

@booklet{EasyChair:4807,
  author    = {Abubakar Ibrahim Muhammad and R. P. Singh and Yusuf Ibrahim},
  title     = {Face Recognition with Particle Swarm optimization (PSO) and Support Vector Machine (SVM)},
  howpublished = {EasyChair Preprint 4807},
  year      = {EasyChair, 2020}}