DOIONLINE 
DOIONLINE Publish In |
International Journal of Advances in Electronics and Computer Science-IJAECS |
 Journal Home Volume Issue |
||||||||
Issue |
Volume-10,Issue-6 ( Jun, 2023 ) | |||||||||
Paper Title |
Contact-Based and Contactless Fingerprint Matching Framework Based on a Fine-Tuned Vision Transformer Model | |||||||||
Author Name |
Mansi Sharma, Shrishti Goyal, Shagun Yadav, Ela Kumar, Garima Garg | |||||||||
Affilition |
Dept. of Computer Science and Engineering Indira Gandhi Delhi Technical University for Women Delhi, India | |||||||||
Pages |
150-157 | |||||||||
Abstract |
This research paper focuses on the matching of contact-based and contactless fingerprints using the "Hong Kong Polytechnic University Contactless 2D to Contact-based 2D Fingerprint Images Database"[1], which contains both types of fingerprint images obtained from a large number of people. Contactless fingerprint sensors have become increasingly popular due to their convenience and hygienic properties. This paper presents the experimental setup and evaluation methodology used to assess the performance of deep neural network-based matching algorithms. Due to the difference in nature of the acquisition of contact and contactless fingerprints, we pre-process both fingerprints to enhance the image quality. In our work, we have compared the performance of the Fine-Tuned Vision Transformer Model to that of the Sequential Convolutional Neural Network (CNN). Experimental results demonstrated that the proposed method, i.e. The Fine-Tuned Vision Transformer Model surpasses state-of-the-art approaches in terms of accuracy and efficiency. Keywords - Contact-Based Fingerprint; Contactless Fingerprint; Biometrics; Fingerprint Pre-Processing; Deep Learning; Fingerprint Recognition | |||||||||
| View Paper | ||||||||||
