Improving Image Quality Assessment Based on the Combination of the Power Spectrum of Fingerprint Images and Prewitt Filter
Journal
Applied Sciences (Switzerland)
Journal Volume
12
Journal Issue
7
Date Issued
2022
Author(s)
Abstract
The assessment of fingerprint image quality is critical for most fingerprint applications. It has an impact on the performance and compatibility of fingerprint recognition, authentication, and built-in cryptosystems. This paper developed an improved fingerprint image quality assessment derived from the image power spectrum approach and combined it with the Prewitt filter and an improved weighting method. The conventional image power spectrum approach and our proposed approach were implemented for accuracy and reliability tests using good, faulty, and blurred fingerprint images. The experimental results showed the proposed algorithm accurately identified the sharpness of fingerprint images and improved the average difference in FIQMs to 61% between three different levels of blurred fingerprints compared with that achieved by a conventional algorithm. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
Subjects
fingerprint; image power spectrum; image processing; image quality assessment; Prewitt filter
SDGs
Type
journal article