Fingerprint orientation estimation and segmentation based on Log-Gabor filter

A robust technique of fingerprint orientation estimation and segmentation based on Log-Gabor filter is proposed. Discrete orientation field is computed through fusion of 8 filtered images by Log-Gabor filter. The gray features of fusion image are robust in spite of different gray features in original fingerprint images. An adaptive threshold according to the histogram is robust to exclude non-ridge areas. Orientation Reliability is defined on the orientations of blocks to discriminate the disordered ridge like areas, in which false minutiae might be extracted. The fusion of the two segmentations and post-processing are introduced to get segmented result image. Experiments show that the proposed orientation estimation and composite segmentation technique is effective and robust to different contrast areas and disordered ridge areas in one image.