An efficient retina pattern recognition algorithm (RPRA) towards human identification

In this paper an automatic person identification algorithm is proposed based on retina pattern recognition. Our proposed method follows the steps firstly reference point detection to compensate the translational and rotational displacements, secondly blood vessel segmentation to identify blood vessel intersection points properly and finally matching the intersection points. The maximum principal curvature of the Hessian matrix of the intensity image is used for blood vessel extraction and number of matched blood vessel intersection points between two patterns is used to quantify the degree of matching. The validity of the results is then verified with concrete examples.