Partial and Latent Fingerprint Image Enhancement

Only available on StudyMode
  • Download(s) : 114
  • Published : February 19, 2013
Open Document
Text Preview
Pattern Recognition Letters 32 (2011) 107–113

Contents lists available at ScienceDirect

Pattern Recognition Letters
journal homepage: www.elsevier.com/locate/patrec

Enhancement of feature extraction for low-quality fingerprint images using stochastic resonance Choonwoo Ryu a,1, Seong G. Kong a,⇑, Hakil Kim b,2
a b

Department of Electrical and Computer Engineering, Temple University, Philadelphia, PA 19122, USA School of Information and Communication Engineering, Inha University, Incheon 402-751, South Korea

a r t i c l e

i n f o

a b s t r a c t
This paper presents a new approach to enhancing feature extraction for low-quality fingerprint images by adding noise to the original signal. Feature extraction often fails for low-quality fingerprint images obtained from excessively dry or wet fingers. In nonlinear signal processing systems, a moderate amount of noise can help amplify a faint signal while excessive amounts of noise can degrade the signal. Stochastic resonance (SR) refers to a phenomenon where an appropriate amount of noise added to the original signal can increase the signal-to-noise ratio. Experimental results show that Gaussian noise added to lowquality fingerprint images enables the extraction of useful features for biometric identification. SR was applied to 20 fingerprint images in the FVC2004 DB2 database that were rejected by a state-of-the-art fingerprint verification algorithm due to failures in feature extraction. SR enabled feature extraction from 10 out of 11 low-quality images with poor contrast. The remaining nine images were damaged fingerprints from which no meaningful features can be obtained. Improved feature extraction using SR decreases an equal error rate of fingerprint verification from 6.55% to 5.03%. The receiver operating characteristic curve shows that the genuine acceptance rates are improved for all false acceptance rates. Ó 2010 Elsevier B.V. All rights reserved.

Article history: Received 28 September 2009 Available online 1 October 2010 Communicated by T.K. Ho Keywords: Fingerprint feature extraction Stochastic resonance Fingerprint recognition Low-quality fingerprint

1. Introduction Fingerprint verification has been widely accepted as a key biometric identification technique in commercial and law enforcement applications. Most commercially available fingerprint recognition systems depend on reliable extraction of feature points from fingerprint images for matching with reference features (Maltoni et al., 2003). Fingerprint recognition fails when no distinct features can be extracted from input fingerprint images. Such lowquality fingerprint images usually contain weak patterns of ridges and valleys due to the surface conditions of the fingertips, humidity, improper finger pressure, or even irregular ridge patterns caused by skin damage, wrinkles, or cracks. Fingerprint feature extractors reject an input fingerprint image if any meaningful fingerprint feature cannot be obtained. Such rejection helps prevent unnecessary matching of images that will subsequently result in incorrect matches. This preprocessing can be more critical in one-to-many identification systems. However, biometric identification systems with high input rejection rates have limited usability due to frequent ⇑ Corresponding author. Tel.: +1 215 204 7932; fax: +1 215 204 5960. E-mail addresses: choonwoo@temple.edu (C. Ryu), skong@temple.edu (S.G. Kong), hikim@inha.ac.kr (H. Kim). 1 Tel.: +1 215 204 3160; fax: +1 215 204 5960. 2 Tel.: +82 32 860 7385; fax: +82 32 873 8970. 0167-8655/$ - see front matter Ó 2010 Elsevier B.V. All rights reserved. doi:10.1016/j.patrec.2010.09.008

failure in enrollment and recognition. Fingerprint recognition systems include an image enhancement component to help a feature extractor find reliable features from low-contrast input fingerprint images. Fingerprint enhancement techniques are often based on local ridge directional binarization (Ratha et al., 1995), Gabor filter (Hong et al.,...
tracking img