Robust Face Recognition under Difficult Lighting Conditions
Journal: The International Journal of Technological Exploration and Learning (Vol.1, No. 1)Publication Date: 2012-08-15
Authors : S.S. Ghatge V.V. Dixit;
Page : 1-4
Keywords : Face recognition; local ternary patterns; local binary pattern; and Kernel principal component analysis;
Abstract
? This paper addresses the problem of illumination effects on Face recognition and works for an approach to reduce their effect on recognition performance. More broadly, a simple and efficient preprocessing chain that eliminates most of the effects of changing illumination while still preserving the essential appearance details that are needed for recognition. Using local ternary patterns (LTP), a generalization of the local binary pattern (LBP) local texture descriptor that is more discriminant and less sensitive to noise in uniform regions. We also show that replacing comparisons based on local spatial histograms with a distance transform based similarity metric further improves the performance of LBP/LTP based face recognition; and Robustness is still improved by adding Kernel principal component analysis (PCA) feature extraction.
Other Latest Articles
- STABILITY INDICATING ASSAY METHOD DEVELOPMENT AND VALIDATION OF DRONEDARONE HYDROCHLORIDE IN ITS BULK FORM BY RP-HPLC
- UNDERSTANDING INTER CLAN SOCIAL DISTANCE AMONG THE KURIA ETHNIC GROUP IN TANZANIA
- GENDER AND EDUCATION OPPORTUNITIES IN TANZANIA: “DO WE BRIDGE THE GAP OF QUALITY?”
- PROMOTING SCIENCE SUBJECTS CHOICES FOR SECONDARY SCHOOL STUDENTS IN TANZANIA: CHALLENGES AND OPPORTUNITIES
Last modified: 2013-09-08 18:23:02