Deep learning-based small-area fingerprint comparison method

Abstract

The invention discloses a deep learning-based small-area fingerprint comparison method. The method comprises the following steps of 1) finding position and direction information of a feature point in a small-area fingerprint; 2) according to the obtained position and direction information of the detail feature point in the step 1), performing rotation normalization on an image by taking the feature point as a center and the direction of the feature point as an X axis, and capturing a small block B of a set size; 3) performing convolutional network training: adopting a deep residual error network for a network model of a convolutional neural network, and training a training sample by using a Caffe framework; 4) performing semantic feature extraction; 5) performing fingerprint registration: enabling a user to perform registration in combination with a corresponding instruction in a registration process, wherein a registration template is composed of a feature point union set of a registration fingerprint image; and 6) performing fingerprint comparison, wherein a comparison score is determined by a mean value of a plurality of maximum values of similarity in to-be-matched images and the registration template. The deep learning-based small-area fingerprint comparison method provided by the invention is effectively suitable for small-area fingerprint comparison and is high in reliability.

Description

technical field [0001] The invention relates to technical fields such as neural network, image processing, pattern recognition, and fingerprint comparison, in particular to a comparison method for small-area fingerprints, which is suitable for identity authentication of smart mobile devices, access control systems, notebooks and other devices. Background technique [0002] With the advancement of science and technology, the traditional identity verification methods relying on citizen ID cards, work permits, and personal passwords have been unable to meet people's increasing needs for security and convenience due to their own shortcomings and deficiencies. And born. Biometric technology belongs to the category of pattern recognition that utilizes the inherent biological and behavioral characteristics of the human body for identity authentication. With the continuous improvement of image processing and pattern recognition technology, fingerprint recognition technology is wide...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the fact that the performance of the existing fingerprint comparison method for small-area fingerprint comparison cannot meet the actual use requirements, the present invention proposes a small-area fingerprint comparison based on deep learning that is effective for small-area fingerprint comparison and has good reliability. method

Images