Latent Fingerprint Matching: Performance Gain via Feedback from Exemplar Prints

Abstract

Abstract-Latent fingerprints serve as an important source of forensic evidence in a court of law. Automatic matching of latent fingerprints to rolled/plain (exemplar) fingerprints with high accuracy is quite vital for such applications. However, latent impressions are typically of poor quality with complex background noise which makes feature extraction and matching of latents a significantly challenging problem. We propose incorporating top-down information or feedback from an exemplar to refine the features extracted from a latent for improving latent matching accuracy. The refined latent features (e.g. ridge orientation and frequency), after feedback, are used to re-match the latent to the top K candidate exemplars returned by the baseline matcher and resort the candidate list. The contributions of this research include: (i) devising systemic ways to use information in exemplars for latent feature refinement, (ii) developing a feedback paradigm which can be wrapped around any latent matcher for improving its matching performance, and (iii) determining when feedback is actually necessary to improve latent matching accuracy. Experimental results show that integrating the proposed feedback paradigm with a state-of-the-art latent matcher improves its identification accuracy by 0.5-3.5 percent for NIST SD27 and WVU latent databases against a background database of 100k exemplars.

Security and Accuracy of Fingerprint-Based Biometrics: A Review

“…By using a total variation decomposition model, the piecewise-smooth background noise can be removed and several overlapping patches are defined and used for latent enhancement, leading to better matching performance. Also, Araro et al [73] incorporated feedback information from an exemplar to refine the extracted features from a latent fingerprint image with the eventual goal of increasing the matching accuracy. [72]).…”

Fingerprint: A Unique and Reliable Method for Identification

“…Like patent fingerprint, plastic fingerprint are easily seen by human eye and do not require additional processing for visibility purpose. 65,66 …”

Enhanced Minutiae Extraction for High-Resolution Palmprint Recognition

“…In this paper, we assume that there is only one valid segment for an input palmprint image. Therefore, only the maximum valid segment is selected as the region of interest (ROI) of the palmprint image, 12 which is recorded by a binary mask with 1 indicating a valid pixel and 0 representing an invalid pixel.…”

“…Three representative methods are commonly used to estimate the local ridge orientation of highresolution palmprint images, including the Gabor¯lter-based method, discrete Fourier transform (DFT), and gradient-based methods. Among them, the Gabor lter-based method 12 applies a bank of Gabor¯lters to multiply the frequency spectrum of the local area and then selects the orientation of the Gabor¯lter achieving the maximum response as the local ridge orientation. The Gabor¯lter-based method is time-consuming due to its high computational complexity.…”

“…An e®ective way 12 for calculating the local ridge density is based on the ridge number at a certain window. Speci¯cally, a rectangular area centered at a pixel is de¯ned, and the edges of which are along the local ridge orientation and the perpendicular orientation of the ridge orientation, respectively.…”