Fingerprint Feature Extraction Using CNN with Multiple Attention Mechanisms

In this paper, we improve the performance of CNN-based fingerprint recognition without increasing the size of CNN, while training CNN on a limited number of data in public databases to guarantee reproducibility. We propose a Texture-Minutiae Network (TMNet) for extracting texture and minutia features based on ResNet-34. We introduce multiple attention mechanisms to TMNet in order to improve performance on fingerprint recognition without increasing the size of the network. Through experiments of performance evaluation using FVC2004 DB1, DB2, and DB3, we demonstrate that the proposed method is more effective than the conventional methods for fingerprint recognition.