Affiliations: [a] School of Computer Science, Wuhan University, Wuhan, China
| [b] School of Computer and Information Engineering, Nanyang Institute of Technology, Nanyang, China
Correspondence:
[*]
Corresponding author. Qiping Hu, School of Computer Science, Wuhan University, Wuhan, China. E-mail: huqp@whu.edu.cn.
Abstract: With the development of technology, fingerprint identification has become an effective means of personal identification, and has been widely used in the fields of public security, custom, banking, network security and other areas requiring identification. Nowadays, many effective methods have been proposed for fingerprint identification, but these methods are not effective in identifying damaged fingerprints, and the correct recognition rate is low. In order to effectively solve the problem of identification and classification of damaged fingerprints, this paper proposes a method for classification of broken fingerprints based on deep learning fuzzy theory. Firstly, after pre-processing the fingerprint, using the bifurcation point and the endpoint in the broken fingerprint image as the minutiae, the feature extraction ability of the deep convolutional neural network is utilized to extract the feature of the damaged fingerprint minutiae. Secondly, the fuzzy rough set is used to reduce the feature. Finally, using the reduced feature uses the Softmax classifier to classify the damaged fingerprint image. The simulation results show that, after preprocessing the damaged fingerprint image, using OPTA algorithm to refine the damaged fingerprint image, the features of the fingerprint image can be extracted effectively by deep convolutional neural network, and then the classification accuracy can be improved by using Softmax classifier to reduce the features.
Keywords: Damaged fingerprint recognition, deep learning, OPTA algorithm, deep convolutional neural network, softmax classifier
