Automated clarity and quality assessment for latent fingerprints

Abstract

Clarity of a latent impression is defined as the discernability of fingerprint features while quality is defined as the amount (number) of features contributing towards matching. Automated estimation of clarity and quality at local regions in a latent fingerprint is a research challenge and has received limited attention in the literature. Local clarity and quality helps in better extraction of features and assessing the confidence of matches. The research focuses on (i) developing an automated local clarity estimation algorithm, (ii) developing an automated local quality estimation algorithm based on clarity, and (iii) understanding the correlation between clarity and quality in latent fingerprints. Local clarity assessment is performed using a 2-D linear symmetric structure tensor. The goodness of orientation field is proposed to estimate the local quality of a latent fingerprint. Experiments on the NIST SD-27 database show that incorporating local clarity information in the quality assessment improves the performance of the matching system.

Multisensor Optical and Latent Fingerprint Database

“…As expected, latent fingerprints in DB4 are poor quality fingerprints with almost 96% of them having a quality score of 5. However, NFIQ is not designed to evaluate the quality of latent fingerprints and a standard (open source) latent fingerprint specific assessment algorithm is still a research challenge [41]. Similarly, there is no exclusive quality measure for simultaneous latent fingerprints (DB5) as well.…”

Overlapped Fingerprint Separation for Fingerprint Authentication

“…Fingerprint and its various features such as minutiae, crossover, core, burification, delta, ridge ending, island, pore. [1]…”

Modified Gabor Filtration and Edge Based Convolution in Neural Network

“…In this paper, they review the works and present the state-of-the-art in fingerprint antispoofing. Contextual Filtering by Maltoni et al They state that it may be "the most widely used technique for fingerprint image enhancement" [8]. In contrast to most other approaches, contextual filtering is especially tuned to fingerprint image enhancement and focusses on its specific characteristics.…”

“…Also we have proposed some methods for orientation field estimation, for example, Wu and Guo et al (2013) [7] propose a SVMbased method for fingerprint and palmprint orientation field estimation. AnushSankaran et al,2013 [8] defined as Clarity of a latent impression is defined as the discernibility of fingerprint features while quality was defined as the amount of features causal towards matching. Automated estimation of clarity and quality at local regions in a latent fingerprint is a study challenge and had received limited attention in the literature.…”