A palmprint recognition algorithm based on binary horizontal gradient orientation and local information intensity

Abstract

Palm will produce the problem of scale inconsistent, rotation and translation during acquisition period,which may cause difficulties in identifying. To solve these problems, a novel palmprint recognition algorithm based on binary horizontal gradient orientation and local information intensity (referred BHOG-LII) has been proposed. First, we use the horizontal gradient template for palmprint image to obtain the gradient image in the horizontal orientation and binarization. Then, the image we get is divided into some girds, and we statistic information intensity of each block as a statistical feature, which are paralleled integration to generate the final feature vector. At last, The chi-square distance is used to classification. Experimental results on PolyU palmprint experiment shows that the proposed method can obtain recognition accuracy up to 99.50%.Compared with some traditional methods, the recognition rate improved significantly. In addition, the proposed algorithm has important significance on the rotation, translation, scaling issues of palmprint recognition.

An Elucidation of Palm Print Recognition Techniques Using Probabilistic and Computational Paradigms

“…There was difficulty in setting appropriate filter parameters as well. A local information intensity and binary horizontal gradient orientation based method was used in (Wu, 2013). It uses an improved edge detection method which reduces the complexity of the algorithm while greatly improving the recognition rate.…”

“…A method using Binary Horizontal Gradient Orientation and Local Information Intensity was introduced by (Wu, 2013). Firstly, they form a gradient function, after which a threshold based binarization process was performed on the image.…”