Journal of System Simulation ›› 2019, Vol. 31 ›› Issue (10): 2174-2180.doi: 10.16182/j.issn1004731x.joss.17-0377

Previous Articles    

A Dorsal Hand Vein Extraction Algorithm for Region of Interest

Li Qi1,2, Cui Jianjiang1, Xue Dingyu1, Geng Hongyu1   

  1. 1. School of Information Science &Engineering, Northeastern University, Shenyang 110819, China;
    2. School of Electronic and Information Engineering, University of Science and Technology, Anshan 114051, China
  • Received:2017-08-04 Revised:2017-11-14 Online:2019-10-10 Published:2019-12-12

Abstract: The rotation and translation of dorsal hand result in deviation, which brings interference during recognizing valid region when collecting dorsal hand vein image. In order to locate valid recognition area quickly, an extraction algorithm for region of interest based on maximum inscribed circle is proposed in view of the characteristics of the collected image. For the collected dorsal hand vein image, this algorithm calculates the center of the maximum inscribed circle and the center of mass, and the rotation angle of the dorsal hand is calculated. The position of the dorsal hand vein image is corrected and the recognition region of interest is extracted by the obtained rotation angle. The algorithm is based on the contour of the dorsal hand and is not affected by human factors. It can eliminate the influence of rotation and translation. Experimental results show that the proposed method has good robustness.

Key words: dorsal hand vein, region of interest, maximum inscribed circle, center of mass, rotation correction

CLC Number: