Face verification using large feature sets and one shot similarity

TitleFace verification using large feature sets and one shot similarity
Publication TypeConference Papers
Year of Publication2011
AuthorsGuo H, Robson Schwartz W, Davis LS
Conference NameBiometrics (IJCB), 2011 International Joint Conference on
Date Published2011/10//
Keywordsanalysis;set, approximations;regression, descriptor;labeled, Face, feature, in, information;face, information;texture, least, LFW;PLS;PLS, recognition;least, regression;color, sets;one, shot, similarity;partial, squares, squares;shape, the, theory;, verification;facial, wild;large

We present a method for face verification that combines Partial Least Squares (PLS) and the One-Shot similarity model[28]. First, a large feature set combining shape, texture and color information is used to describe a face. Then PLS is applied to reduce the dimensionality of the feature set with multi-channel feature weighting. This provides a discriminative facial descriptor. PLS regression is used to compute the similarity score of an image pair by One-Shot learning. Given two feature vector representing face images, the One-Shot algorithm learns discriminative models exclusively for the vectors being compared. A small set of unlabeled images, not containing images belonging to the people being compared, is used as a reference (negative) set. The approach is evaluated on the Labeled Face in the Wild (LFW) benchmark and shows very comparable results to the state-of-the-art methods (achieving 86.12% classification accuracy) while maintaining simplicity and good generalization ability.