Occlusion Invariant Palmprint Recognition with ULBP Histograms

This work presents a palmprint recognition approach based on the local distribution of uniform patterns. Preprocessing segments palmprint region from foreground of image as well as aligns the palmprint along the line between tips of middle finger and mid of wrist. Palmprint texture has line and wrinkles like features which are a type of uniform patterns. Uniform LBP (ULBP) refers to the pattern of uniform appearance with limited discontinuities. ULBP histograms are used as features to handle occlusion upto 36%. Experiments are performed on 400 classes of the PolyU 2D, 600 classes of CASIA and 150 classes of IIITDMJ palmprint database. Correct identification rates of 99.6% for normal palmprints and 99% for randomly occluded palmprints are obtained on PolyU 2D database.