Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

A functional enhancement on scarred fingerprint using sigmoid filtering

Kolivand, H, Hamid, AABA, Asadianfam, S and Rahim, MSM (2022) A functional enhancement on scarred fingerprint using sigmoid filtering. Neural Computing and Applications. ISSN 0941-0643

[img]
Preview
Text
s00521-022-07520-x.pdf - Published Version
Available under License Creative Commons Attribution.

Download (3MB) | Preview

Abstract

Fingerprint has been widely used in biometric applications. Numerous established researches on image enhancement techniques have been done to improve the quality of fingerprint images. However, the production of low-quality images due to the presence of scars remains a challenge in biometrics. The scars damage the fingerprint minutiae information due to broken ridges and they reduce the accuracy of identification. This research developed an image enhancement approach to improve the quality of scarred fingerprint images to generate accurate minutiae extraction. To achieve the aim, the scarred image was improved by removing noise using a new filter, Median Sigmoid (MS), and the corrected ridges were reconstructed using ridges structure enhancement algorithm. This was done to enhance the broken ridges structure. MS filter is a combination of median filter and modified sigmoid function that improves the image contrast and simultaneously removes noise in the fingerprint image. Following that, the filtered image was used in the ridges structure enhancement process. To identify true minutiae, the broken ridges structure in the filtered image needed to be accurately verified. In the ridges structure reconstruction process, an algorithm was enhanced to identify the best value of Sigma parameter (σ) used in the Gaussian Low-pass filter to generate a better orientation image. The image is important to reconstruct the corrupted fingerprint ridges structure. The evaluation for the proposed approach used the National Institute of Standards and Technology Special Database 14, and the results showed a 37% improvement of the quality index in comparison to approaches found in related research. The findings of the evaluation showed that the proposed enhancement approach produced a better minutiae extraction result and this is very significant in the field of fingerprint image enhancement.

Item Type: Article
Uncontrolled Keywords: 0801 Artificial Intelligence and Image Processing; 0906 Electrical and Electronic Engineering; 1702 Cognitive Sciences; Artificial Intelligence & Image Processing
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Divisions: Computer Science & Mathematics
Publisher: Springer Science and Business Media LLC
SWORD Depositor: A Symplectic
Date Deposited: 21 Sep 2022 08:03
Last Modified: 21 Sep 2022 08:03
DOI or ID number: 10.1007/s00521-022-07520-x
URI: https://researchonline.ljmu.ac.uk/id/eprint/17624
View Item View Item