Title: Latent dactyloscopy pairing: presentation attained through feedback from EPITOME

Authors: R. Pugalenthi; F. Sangeetha Francelin Vinnarasi; P. Mohan Kumar; R. Arokia Renjith

Addresses: Department of CSE, St. Joseph's College of Engineering, OMR, Chennai, India ' Department of CSE, St. Joseph's College of Engineering, OMR, Chennai, India ' Department of CSE, Jeppiaar SRR Engineering College, OMR, Chennai, India ' Department of Information Technology, Jeppiaar Engineering College, OMR, Chennai, India

Abstract: Latent fingerprints are recognised as evidence against offenders in law enforcement agencies. The automatic fingerprint identification system (AFIS) method can be applied to rolled and plain fingerprints, which gives results of high accuracy. The latent accuracy will be less due to background noise and poor ridge quality. Also, pairing of latent imaging is a challenging issue. Keeping these in view, this work suggests the pairing of top-down data or feedback from an epitome to filter and to develop a latent pairing accuracy. The exhibited results show that the combination of the proposed feedback pattern with a latent pair of state-of-the-art develops a finding accuracy for WVU datasets and latent NIST SD27 against a background dataset of 100X epitome by 1 to 3.5 percentage. This proves that the combined feedback pattern with the latest results can be carried out in real-time.

Keywords: candidate record; feature filtration; latent fingerprint pairing; epitome feedback.

DOI: 10.1504/IJBIC.2021.114087

International Journal of Bio-Inspired Computation, 2021 Vol.17 No.2, pp.85 - 94

Accepted: 31 Jul 2020
Published online: 08 Apr 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article