DHV image registration using boundary optimization

An image registration method using boundary optimization is proposed to register dorsal-hand vein (DHV) images of different rotation angles. Since image rotation is inevitable during image capture, the proposed method is important in human identification based on DHV images. The proposed method consists of two main procedures, i.e., boundary detection and boundary optimization. Boundary detection is used to create a boundary map, and boundary optimization is used to find the best rotation angle with the boundary map. Simulations and extensive experiments show that the proposed method can reduce equal error rate (EER) efficiently. The experiments also show that the method is fast and can be completed in 50 milliseconds.