Multi-modal identification method based on fingerprints and finger veins

• Main Authors: JIANG YIFAN, GUO JIAN, CHEN RUOXING, TU JIAXIANG, ZHU ZHA, WANG JUAN, WANG SHUXUAN, HAN CHONG, ZHANG QIN
• Format: Patent
• Language: Chinese; English
• Published: 16.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

A multi-modal identification method based on fingerprints and finger veins comprises the following steps: respectively taking collected fingerprints and finger vein pictures as independent inputs of a network for feature extraction and analysis; analyzing the correlation between the fingerprint and the corresponding finger vein through an attention mechanism from the dimensions of the channel and the space, and fusing the characteristics of the fingerprint and the finger vein; and a Softmax function is used to determine a final biological feature recognition result. According to the method, preprocessing operation is simple, only ROI of fingerprints and finger veins needs to be extracted, detail features in the image can be saved to the maximum extent, and extra computer resource consumption is reduced; compared with an existing biological feature recognition method using a single biological mode, the fingerprint image and the finger vein image are fused, discriminative features of the biological features can