A Deep Supervised Lacunarity Analysis Model Based on Weight Adaptive Local Binary Pattern Texture For Palmprint Recognition System

Abstract

In this research, a Deep Supervised Lacunarity Analysis Model based on the Weight Adaptive Local Binary Pattern Texture for Palmprint Recognition (DSLPR) system is proposed for evolving the innovative Palmprint Recognition System (PRS). To reveal the originality of DSLPR system, a new Section-based Contour Lacunarity Analysis based on Weight Adaptive Local Binary Pattern (SCLA-WALBP) feature extraction approach and a Deep Learning Network classifier using a Supervised Algorithm (DLNSANet) are implemented to gain the superior substantiation accuracy rate for accessing the digital content and highly worthy assets. To accomplish the DSLPR system,  Two Dimensional Palmprint Region of Interest (2D-PROI) image is preprocessed (PI), spotted out all tiny edges, ridges, and wrinkles of PI using Weight Adaptive Local Binary Pattern (WALBP) algorithm, and traced all outlines of the PI using a canny edge detection algorithm. SCLA-WALBP approach is invoked to produce an exclusive feature vector. Classify this feature vector using DLNSANet classifier approach to substantiate the authentic person with more accuracy rate. This research work experiment is employed on PolyU’s multi-spectral 2D-PROI image database. This DSLPR system has been appraised with 99% of authentication accuracy.