Human Face Identification based on Optimal Sparse Features

M Risheek Sharma,Shijin Kumar P S,B Koteswarrao,K Sravan Kumar,K Akhil Vardhan

doi:10.35940/ijeat.b3098.129219

M Risheek Sharma, Shijin Kumar P S + Show 3 more

Open Access

https://doi.org/10.35940/ijeat.b3098.129219

Copy DOI

Abstract

Security of human being is an important aspect in the context of data communication. To maintain security, technology is being developed from alpha-numeric passwords to biometric scanners. Recent advancement in security is the user authentication using face recognition. But the flaws in existing face recognition systems are yet to be addressed. This paper discusses solutions to the issues encountered by face recognition systems. Sparsity based classification is performed in this work. This method can handle errors occurs due to compress in and occlusion in a robust manner. We suggest a comprehensive classification algorithm characterized by sparse representation and 1l -minimization. In this method, the feature points and selection of features are not critical. The effect of change in occlusion can be easily addressed by using this optimal sparse representation based classification (OSRC) algorithm.

Highlights

Face recognition can be considered as a difficult and hot study subjects in last few years
In recognition rate, and there is some improvement in computational time
Though the recognition rate is almost equal for both algorithms, there is a noticeable reduction in computational time

Summary

INTRODUCTION

Face recognition can be considered as a difficult and hot study subjects in last few years. Traditional face recognition algorithms adhere to geometry [2] based approach or piecewise [6] appearance oriented approach For face recognition, these techniques employ raw facial images. Chu et al [11] developed a geometry based feature extraction technique for the recognition of facial images in severe conditions. This method provided a recognition rate of 96.4%. Wright et al [12] proposed a simple face recognition system based on sparse representation This method is highly robust against corruption due to occlusion.

METHODOLOGY

EXPERIMENTAL RESULTS

CONCLUSION