Enhancement of feature extraction for low-quality fingerprint images using stochastic resonance

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 low-quality 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.

Research highlights
► Fingerprint recognition fails when no distinct features can be extracted.
► Adding an appropriate amount of noise can enhance the detection of faint signals.
► Stochastic resonance improves feature extraction from low-quality fingerprint images.
► Genuine acceptance rate is increased in the entire range of false acceptance rates.