Research And Realization Of Fingerprint Image Preprocessing Algorithm

For the needs of security ,veracity and convinience ,biometrics technology has been applied to identity identifying more and more.As the main technology of biometrics,fingerprint identification is recoganized as the study hotspot in China and abroad.The fingerprint image preprocessing system is mainly studied the parts below: Fingerprint image segmentation; Fingerprint image enhancement; Fingerprint image thinning; Post processing of thinned fingerprint image.Two segmentation methods are used and compared in the fingerprint segmentation: variance method and orientation method.Gabor filter has both the frequency-selective and orientation-selective properties and has optimal joint in both the spatial and frequency domains.Therefore, it is appropriate to use the Gabor filter to establish the bandpass filters to enhance the true ridge structure.First we obtain the low-frequency subimage by wavelet transform. The orientation is valued on the subimage and evaluated to original fingerprint image also smoothed by getting rid of the sharp-angled feature point. Also the paper has improved the frequency algorithm, the size of Gabor filter.The adaptive Gabor filter can adapt the fingerprint database with different sized fingerprint images.We use the OPTA to make thinning ,also we compare the OPTA and the traditional 8 neighbored thinning algorithms.The after-thinning preceeding step is finished only with the signed misfeature point. We don't change the after-thinning picture but get rid of the misfeature point when picking up the feature point.The fingerprint image preprocessing system, tested by a series of experiments, is proven to be effective.