Deep Learning-Enhanced Fingerprint Generation and Security Verification in the Context of Siamese Network Matching Models
Junyan Guo · 2023
Fingerprint recognition, a widely adopted technology in various domains, confronts significant challenges in both technical and practical realms. Therefore, it is essential to develop an effective algorithm to improve the accuracy of fingerprint recognition. In this study, a novel method is proposed to generate fake fingerprint images by Deep Convolution Generative Adversarial Networks (DCGAN) network, utilizing FVC2002 and FVC2004 as the dataset. Furthermore, a dataset consisting of 6, 000 fingerprint pairs, with the first 3, 000 pairs collected from the same individual and the remaining 3, 000 pairs from different individuals, is employed to train a Siamese Network. Finally, the real fingerprint image and the generated fingerprint image are used as two inputs to the Siamese Network to verify whether any two fingerprint images can be incorrectly matched. Experimental results indicate that DCGAN has an excellent ability to generate fingerprint images, although a small portion of the generated images have defects, which may be caused by the model training the blank part of the images as important features, etc. Additionally, the security verification experiment employing the Siamese Network reveals potential vulnerabilities in the fingerprint recognition system, possibly stemming from the network’s focus on localized similarities between the two input fingerprint images.