Finger Vein Recognition Based on Local Opposite Directional Pattern

Abstract

AbstractLocal operator has already been used in the finger vein recognition. But the traditional algorithms, such as Local Binary Pattern (LBP) Local Directional Pattern (LDP) and so on, are lack of effective extraction of the gradient information of the image. In order to overcome the shortcomings of the traditional methods, this paper proposed a Local Opposite Directional Pattern (LODP) operator for finger vein recognition motivated from the Local Gradient Pattern (LGP), LDP, local Ternary Pattern (LTP) operators. The LODP operator mainly extracts the gradient information of the finger vein images. This operator uses local 3×3 masks to make the convolution with the images. After comparing the opposite pixels, three-valued encoding mode has been used. Then the center pixel will be set with a new binary value. The experimental results showed that the LODP operator behaves better than LGP, LDP, LTP operators in extracting the features of finger vein images.KeywordsFinger veinGradientOpposite direction pattern