Finger vein recognition scheme based on convolutional neural network using curvature gray image

Finger vein recognition technology refers to the use of finger vein angiogra-phy image authentication technology, which has became one of the hot spots of biometric identification technique. Conventional finger vein recognition technology is based on image features, and its main idea is to extract features of the overall image or features of the vein pattern. Because there are a large amount of redundant data based on features acquired from the whole finger vein image, the time complexity is high, and the features extracted from the vein pattern are greatly affected by the image segmentation algorithm. In order to improve the accuracy of the finger vein recognition algorithm under small samples, a finger vein recognition algorithm based on convolutional neural network using curvature gray images is proposed in this paper. First, we calculate the curvature of a finger vein image using a two-dimensional Gaussian template. Then we extract two gray images of the finger vein image with different scales and add these two images to ob-tain the final curvature gray image. Using curvature gray images as input, an improved convolutional neural network is trained and used to recognize the identity of the input curvature gray image. Experimental results show that our scheme is effective and better than existing schemes.