Share Email Print

Proceedings Paper

Fingerprint image enhancement & denoising
Author(s): Akhilesh R. Upadhyay; Ramesh K. Choudhary; Sanjay N. Talbar
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Fingerprint images vary in quality. The performance of a fingerprint recognizer greatly depends on the fingerprint image quality. Different types of noises in the fingerprint images create greater difficulty for recognizers. Fingerprint image enhancement is an essential preprocessing step in fingerprint recognition applications. Numerous methods like Gaussian blurring, Median Filtering, Canny thresholding have been described in the paper. Generally noisy valley pixels and the pixels in the interrupted ridge may be observed. The primary goal of processing a noisy signal is to obtain a reconstruction as close to the original clean signal as possible. Scale-based analysis has recently played an increasingly important role in image analysis. Scale space is an isotropic method that smooths signals with Gaussian kernel uniformly by increasing scale. This paper describes a new approach to fingerprint image enhancement, the filter is based on Nonlinear Anisotropic Diffusion approach. Experimental results show that our enhancement algorithm improves the performance of the fingerprint verification system and makes it more robust with respect to the quality of input fingerprint images.

Paper Details

Date Published:
PDF: 6 pages
Proc. SPIE 6497, Image Processing: Algorithms and Systems V, 649719; doi: 10.1117/12.696281
Show Author Affiliations
Akhilesh R. Upadhyay, Asia Pacific Institute of Information Technology (India)
Ramesh K. Choudhary, Asia Pacific Institute of Information Technology (India)
Sanjay N. Talbar, Institute of Engineering & Technology (India)

Published in SPIE Proceedings Vol. 6497:
Image Processing: Algorithms and Systems V
Jaakko T. Astola; Karen O. Egiazarian; Edward R. Dougherty, Editor(s)

© SPIE. Terms of Use
Back to Top