Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.32985/ijeces.13.7.7

Deep learning approach for Touchless Palmprint Recognition based on Alexnet and Fuzzy Support Vector Machine

John Prakash Veigas ; Department of Information Science and Engineering, A J Institute of Engineering and Technology, Kottara Chowki, Mangaluru, India
Sharmila Kumari M ; Department of Computer Science Engineering, P A College of Engineering, Mangaluru, India


Puni tekst: engleski pdf 1.343 Kb

str. 551-559

preuzimanja: 358

citiraj


Sažetak

Due to stable and discriminative features, palmprint-based biometrics has been gaining popularity in recent years. Most of the traditional palmprint recognition systems are designed with a group of hand-crafted features that ignores some additional features. For tackling the problem described above, a Convolution Neural Network (CNN) model inspired by Alex-net that learns the features from the ROI images and classifies using a fuzzy support vector machine is proposed. The output of the CNN is fed as input to the fuzzy Support vector machine. The CNN's receptive field aids in extracting the most discriminative features from the palmprint images, and Fuzzy SVM results in a robust classification. The experiments are conducted on popular contactless datasets such as IITD, POLYU2, Tongji, and CASIA databases. Results demonstrate our approach outperformers several state-of-art techniques for palmprint recognition. Using this approach, we obtain 99.98% testing accuracy for the Tongji dataset and 99.76 % for the POLYU-II datasets.

Ključne riječi

Palmprint Recognition; Deep learning; Support Vector Machine; Fuzzy

Hrčak ID:

284951

URI

https://hrcak.srce.hr/284951

Datum izdavanja:

30.9.2022.

Posjeta: 855 *