Welcome to the InfoSci Platform
Generalization and Efficiency on Finger Print Presentation Attack Anomaly Detection

Generalization and Efficiency on Finger Print Presentation Attack Anomaly Detection

Hemalatha J., Vivek V., Kavitha Devi M. K., Sekar Mohan
Copyright: © 2023 |Pages: 18
ISBN13: 9781799888925|ISBN10: 1799888924|ISBN13 Softcover: 9781799888932|EISBN13: 9781799888949
DOI: 10.4018/978-1-7998-8892-5.ch023
Cite Chapter Cite Chapter

MLA

J., Hemalatha, et al. "Generalization and Efficiency on Finger Print Presentation Attack Anomaly Detection." Handbook of Research on Computer Vision and Image Processing in the Deep Learning Era, edited by A. Srinivasan, IGI Global, 2023, pp. 362-379. https://doi.org/10.4018/978-1-7998-8892-5.ch023

APA

J., H., V., V., M. K., K. D., & Mohan, S. (2023). Generalization and Efficiency on Finger Print Presentation Attack Anomaly Detection. In A. Srinivasan (Ed.), Handbook of Research on Computer Vision and Image Processing in the Deep Learning Era (pp. 362-379). IGI Global. https://doi.org/10.4018/978-1-7998-8892-5.ch023

Chicago

J., Hemalatha, et al. "Generalization and Efficiency on Finger Print Presentation Attack Anomaly Detection." In Handbook of Research on Computer Vision and Image Processing in the Deep Learning Era, edited by A. Srinivasan, 362-379. Hershey, PA: IGI Global, 2023. https://doi.org/10.4018/978-1-7998-8892-5.ch023

Export Reference

Mendeley
Favorite

Abstract

Biometric identification systems are highly used for verification and identification like fingerprint recognition, voice recognition, face recognition, etc. The very famous biometric technique is fingerprint recognition. A fingerprint is the pattern of ridges and valleys on the surface of a fingertip. The endpoints and crossing points of ridges are called minutiae. The basic assumption is that the minutiae pattern of every finger is unique and does not change during one's life. In the present era, fingerprint-based biometric authentication system gets popularized, but still, this biometric system is vulnerable to various attacks, particularly presentation attacks. This chapter explains how the knowledge-driven neural networks work on fingerprint anomaly detection. In addition, the various features available to detect the anomaly in biometric are also discussed.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.