Title: Modified FFT features for fingerprint matching

Authors: Sangita D. Bharkad; Manesh Kokare

Addresses: Department of Electronics and Telecommunication Engineering, S.G.G.S. Institute of Engineering and Technology, Vishnupuri, Nanded 431603, Maharashtra, India ' Department of Electronics and Telecommunication Engineering, S.G.G.S. Institute of Engineering and Technology, Vishnupuri, Nanded 431603, Maharashtra, India

Abstract: A novel approach for fingerprint feature extraction is proposed by using modified Fast Fourier Transform (FFT) coefficients. The proposed method extracts the significant features from small portion of cropped fingerprint image using frequency-shifting property of discrete Fourier transform. The performance of the proposed method is evaluated on standard fingerprint database available at website of Bologna University. Results of the proposed method are compared with Discrete Wavelet Transform (DWT) and FFT-based method. The proposed method improves Genuine Acceptance Rate (GAR) from 77.14% to 96.73% over DWT and 88.26% to 96.73% over traditional FFT with very low computational complexity.

Keywords: biometrics; FFT; fast Fourier transform; DWT; discrete wavelet transform; fingerprint matching; feature extraction; fingerprint images.

DOI: 10.1504/IJSISE.2013.054791

International Journal of Signal and Imaging Systems Engineering, 2013 Vol.6 No.3, pp.150 - 157

Received: 08 Feb 2011
Accepted: 09 Aug 2011
Published online: 20 Sep 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article