Missing data reconstruction using Gaussian mixture models for fingerprint images

• NCJ Number: 308371
• Author(s): Sos S. Agaian; Rushikesh D. Yeole; Shishir P. Rao; Marzena Mulawka; Mike Troy; Gary Reinecke
• Date Published: 2016
• Grant Number(s): 2014-IJ-CX-K003
• Agencies: NIJ-Sponsored
• Publication Type: Research (Applied/Empirical)

Annotation

This publication discusses the use of Gaussian mixture models for missing data reconstruction for fingerprint images.

Abstract

This paper introduces a method for missing data reconstruction using Gaussian mixture models for fingerprint images. One of the most important areas in biometrics is matching partial fingerprints in fingerprint databases. Recently, significant progress has been made in designing fingerprint identification systems for missing fingerprint information. However, a dependable reconstruction of fingerprint images still remains challenging due to the complexity and the ill-posed nature of the problem. In this article, both binary and gray-level images are reconstructed. This paper also presents a new similarity score to evaluate the performance of the reconstructed binary image. The offered fingerprint image identification system can be automated and extended to numerous other security applications such as postmortem fingerprints, forensic science, investigations, artificial intelligence, robotics, all-access control, and financial security, as well as for the verification of firearm purchasers, driver license applicants, etc. This publication is an updated version of one originally published on 25 May 2016 that was replaced with a revised version on 16 June 2016. (Published Abstract Provided)