A Location Method Based on Eight- Neighborhood Chain Code for Palmprint Image
【摘要】：正The crucial issue of precise location for on-line palmprint image was to detect corner of hand-shape contour accurately. The existing corner detection algorithm cannot extract corner useful for location automatically. Through analyzing the regularity of chain-code of hand-shape contour , a rapid and effective corner-detection method was proposed in this paper. Firstly, the method of LOG operator and eight neighborhood boundary -tracking algorithm was made use of to extract the hand-shape contour and its chain-code. Then, according to the regularity of hand-shape contour chain-code around comer, the corner of hand-shape contour was detected accurately. Finally, establish a coordinate system according to the corner detected and locate the palmprint image. The experiment results demonstrate the effectiveness and rapidness of the proposed method.