![Sample our Engineering & Technology journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5933/TOC-Subject-Sample-2021-Engineering-Tech.jpg"})
Abstract
In this study, we statistically analysed biometric-fingerprint images for personal identification. For each of the original images, a 129×129 region of interest was extracted and transformed into a co-occurrence matrix. Four different types of relative position distances were used to generate these matrices. The results were then analysed twice: first by the Program for Rate Estimation and Statistical Summaries (PRESS) and then by the Pattern Recognition and Image Processing Laboratory (FVC2002) testing protocol. The efficiency of the proposed method was demonstrated by the experimental results. In addition, it was found that greater relative-position distances produced lower error equal rates.