Fingerprint image preprocessing method based on the continuous spectrum analysis

Abstract

The spectral field analysis is one key means for processing the fingerprint image in automatic fingerprint identification technology. The fingerprint ridge distance can be acquired and the fingerprint image can be enhanced accurately using the spectral filed analysis method. However, traditional Fourier transform spectral analysis method had the worse redundancy degree in estimating the ridge distance because it was based on the two-dimension discrete Fourier spectrum. To introduce the sampling theorem into the fingerprint image processing method and transform the discrete spectrum into the continuous spectrum. To acquire the local peak points adopting artificial immune network optimization algorithm and then segment valid fingerprint image region from background region or stressed-noised region, obtain ridge distance and ridge orientation of valid fingerprint regions based on the continuous spectrum analysis in frequency field. The experimental results indicate that the method has higher adaptability and can improve the accuracy of the automatic fingerprint identification system effectively. © 2012 Springer Science+Business Media B.V.