Fingerprint Ridge Frequency Estimation in the Fourier Domain

Abstract

Ridge frequency is an important parameter in fingerprint image processing and feature extraction. However, ridge frequency estimation is a difficult task in noisy fingerprint images. A simple and accurate method for the computation of fingerprint ridge frequency using the Fourier spectrum is proposed. The results of the experiments conducted on a collection of fingerprints as well as a quantitative method for performance evaluation based on a Gabor filter-bank are presented. The proposed method is robust with respect to noise and reliable frequency images are obtained.

Keywords

• biometrics
• feature extraction
• fingerprint recognition
• identification of persons
• spectral analysis