Robust Vein Recognition against Rotation using Kernel Sparse Representation

Sparse representation due to the advantages such as noise-resistance and having a strong mathematical theory has been noticed as a powerful tool in the recent decades. In this work, using the sparse representation, kernel trick, and the different technique of region of interest (ROI) extraction presented in our previous work, a new and robust method against rotation is introduced for the dorsal hand vein recognition. In this method, in order to select ROI, by changing the length and angle of the sides, the undesirable effects of hand rotation during taking images are largely neutralized. Thus depending on the amount of hand rotation, ROI in each image will be different in size and shape. On the other hand, due to the same direction distribution on the dorsal hand vein patterns, we use the kernel trick on sparse representation for classification. As a result, most samples with different classes but the same direction distribution will be classified properly. Using these two techniques leads to introduce an effective method against hand rotation for dorsal hand vein recognition. An increase of 2.26% in the recognition rate is observed for the proposed method when compared to the three conventional SRC-based algorithms and three classification methods based on sparse coding that use dictionary learning.