Matching of contactless and contact fingerprints has increased its attention in recent days. There have been only a few attempts to match contactless and contact-based fingerprints using Convolutional neural network (CNN) model. We collected a publicly available dataset of contactless and their corresponding contact-based fingerprints from Hong Kong Polytechnic University. The dataset consists of 3,120 contactless fingerprints and corresponding contact fingerprint images from 260 fingers of 6 impressions each. Due to the difference in nature of acquisition of both contact and contactless fingerprint first, we pre-process both the fingerprints to enhance the image quality. We train the CNN model using both fingerprints. In our work, we used the Sequential CNN model to increase the accuracy of matching contact and contactless fingerprint images
Key Word: contact-based fingerprints, contactless fingerprints, Convolutional neural network, Matching.
[1]. C. Lin and A. Kumar, "Matching contactless and contact-based conventional fingerprint images for biometrics identification," IEEE Transactions on Image Processing, vol. 27, no. 4, pp. 2018.
[2]. C. Lin and A. Kumar, "A CNN-based framework for comparison of contactless to contactbased fingerprints," IEEE Transactions on Information Forensics and Security, vol. 14, no. 3, pp. 662–676, 2019.
[3]. Steven A. Grosz, Joshua J. Engelsma and Anil K. Jain," C2CL: Contact to Contactless Fingerprint Matching", 2021.
[4]. A. Dabouei, S. Soleymani, J. Dawson, and N. M. Nasrabadi, "Deep contactless fingerprint unwarping," in 2019 International Conference on Biometrics (ICB), 2019, pp. 1–8.
[5]. P. Wild, F. Daubner, H. Penz, and G. F. Dom´ınguez, "Comparative test of smartphone finger photo vs. touch-based cross-sensor fingerprint recognition," in 2019 7th International Workshop on Biometrics and Forensics (IWBF). IEEE, 2019, pp. 1–6. .