Fingerprint pre-segmentation method based on Mean Shift Algorithm

In the research or application of fingerprint images, people focus on the region where the ridges are seen. The background region of the whole image contains various degrees of noise caused by unevenly pressing of the fingerprint and the contaminated camera lens. This phenomenon calls for the considerations of noise elimination, image enhancement, and pre-segmentation. Mean Shift algorithm is a nonparametric statistics method that searches for the most approximate mode to the sample distribution. The fingerprint pre-segmentation method based on mean shift algorithm was studied and applied in a number of images stored in FVC2004 image Database. The results show that the Mean Shift method is applicable to most images. There are very few results are out of the optimal ones.