Contactless Fingerprint Recognition and Fingerprint Spoof Mitigation using CNN
Sunil B Nirmal1, Kishor S Kinage2
1Sunil B Nirmal, currently a final year M Tech student of Pimpri Chinchwad College of Engg. Pune University, India.
2Dr.Kishor Kinage, professor at Pimpri Chinchwad college of engg, Pune, India.
Manuscript received on November 19, 2019. | Revised Manuscript received on November 29 2019. | Manuscript published on 30 November, 2019. | PP: 9271-9275 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9420118419/2019©BEIESP | DOI: 10.35940/ijrte.D9420.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Contactless identification of fingerprints has gained considerable attention as it can offer more hygienic and accurate personal identification. Despite these benefits, contactless 2D imagery often leads to partial 2D fingerprints as it requires relatively higher user cooperation during contactless 2D imagery. This paper develops a CNN framework for recognizing contactless fingerprint images–based on database. Our framework uses fingerprint minutiae and particular ridge map region to train a CNN first. Over several popular deep learning, our experiments presented in this paper achieve good results with greater accuracy. Experimental results obtained in this paper shows the effectiveness of the proposed approach and illustrate a significant improvement in methods of fingerprint recognition. The proposed work also helps to mitigate spoofing of fingerprints, thus providing greater security.
Keywords: Bio-Metric, Neural Network, CNN, Authentication, Spoofing.
Scope of the Article: Pattern Recognition.