A Face Recognition Approach Based on Nearest Neighbor Interpolation and Local Binary Pattern
Josky Aïzan, Eugène Cokou Ezin, Cina Motamed · 2016
In this paper, we present a novel approachfor face recognition which consists of a dimensionality reduction of face feature vectors. The image scaling is firstly conducted on an input face image. Then we applied the Local Binary Pattern (LBP) operator by dividing the face imageinto non-overlapped regions. LBP histograms are extracted from each region and concatenated into a single one that represents the face image. Nearest neighbor classifier isused to perform recognition with Chi square function asa dissimilarity measure. Simulation experiments are done using the ORL (Olivetti Research Laboratory) databases howing the efficiency of the proposed approach with 97.5%as recognition rate.