A modified preprocessing method for palmprint recognition

Palmprint recognition attracts more attention for personal authentication in recent years. A key issue to be solved foremost is preprocessing the image to gain a proper sub-area for feature extraction and matching. Due to the images obtained by a digital scanner without any constraint of pegs, distortions including rotation, shift and translation are contained in the palm images which make it hard to locate at correct position in the same direction. A modified preprocessing method with two rotations and two segmentations is proposed. The first rotation makes the acclivitous outer boundary of palm vertical, and then truncates the edge graph with eight intersections of four fingers. The gaps between index finger and middle finger, and that between the ring finger and little finger can be tracked. Align the two points and rotate the image to ensure the line horizontal as the basis of a precise coordinate system for extracting a fixed size region. 2D Gabor filters are used for feature extraction and the verification experimental results demonstrate the effectiveness of the proposed modified preprocessing method