A location algorithm of inner-knuckle-print based on dimension reduction
QI Le-tao · Hebei ke-ji daxue xuebao · 2012
Considering the difficulty of accurately and fast location of ROI of inner-knuckle-print,a new location algorithm is presented forward based on dimension reduction.This algorithm transforms 2-dimension image data to two 1-dimension data by projecting the binary image in vertical and horizontal direction,and then aligns ROI images through the comparison of the two 1-dimension data.This leads to rapid and efficient recognition.The experimental results verify that it is rapid and effective than traditional methods.