文章基本信息

标题：Face Recognition under Different Lighting Conditions Using Multiple Feature Fusion
本地全文：下载
作者：Kothamasu Jahnavi ; K.Satya Prasad
期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：8
页码：14707
DOI：10.15680/IJIRCCE.2017.0508006
出版社：S&S Publications
摘要：Face recognition has received substantial attention from researchers in biometric pattern recognition.The common challenges faced by the face recognition technology are the range of appearance variations due to changesin illumination, pose, facial expression, aging etc.The objective of this paper is to make face recognition reliable underuncontrolled lighting conditions. This is achieved by an integrated framework consisting of illumination normalization,local texture based face representation, robust feature extraction and multiple feature fusion. Each stage increasesresistance to illumination variations. Local ternary pattern, local binary pattern and gabor wavelets are used to extractlocal feature sets.In the proposed method, an additional feature set is extracted using Elongated Multi Block LocalTernary Pattern (EMB-LTP). It improves the reliability of the algorithm. This multiple feature fusion technique canachieve a higher acceptance ratio and a lower rejection ratio compared to the cases where a single feature set is used.
关键词：Biometric pattern recognition; Local Binary Pattern; Local Ternary Pattern; Gabor wavelets