A multi-stage fingerprint image segmentation method

Segmentation is an important step in fingerprint recognition ystem, in which the region of interest can be extracted. his paper presents a novel fingerprint image segmentation method aiming at dealing with low quality fingerprint images. Firstly the mean and variance of gray level in each divided block is used to differentiate the image coarsely. Then two new features intra-consistency and extra-consistency are defined in further segmentation stage and validation stage respectively. They can reflect the texture feature within a block as well as between neighbor blocks, and are utilized to partition the image refinedly, especially for the shadow area and the boundary between foreground and background. Gabor filter is used in this paper and a fast implementation of Gabor filter is adopted. Experimental results show the effectiveness and robustness of the proposed method.