A Fast Denoising Method for Binary Fingerprint Image

X. Liang and T. Asano (Japan)


ordinary morphological operator (OMO), generalized morphological operator (GMO), structuring element (SE),strictness, Euclidean distance transform, useless component.


In this paper we propose a fast method for binary finger print image denoising that employs the generalized and ordinary morphological operators based on Euclidian dis tance transform. This method avoids quite a number of computational redundance. In particular, the computations of denosing step are restricted to a minimum number of pixels. The results show that applying this method on fin gerprint image with impulsive noise and useless compo nents yields a segmentation much closer to that of an expect for extracting the minutia accurately.

Important Links:

Go Back