Genetic Algorithm Based Gabor CNN For Palmprint Recognition
John Prakash Veigas1, M Sharmila Kumari2, Gnane Swarnadh Satapathi3
1John Prakash Veigas*, Dept of ISE, AJ Institute of Engineering and Technology Mangalore affiliated to VTU, Belgaum, India.
2M Sharmila Kumari, Dept of CSE, PACE, Mangalore, India.
3Gnane Swarnadh Satapathi, Dept of ECE, AJIET Mangalore, India.
Manuscript received on March 12, 2020. | Revised Manuscript received on March 26, 2020. | Manuscript published on March 30, 2020. | PP: 4895-4899 | Volume-8 Issue-6, March 2020. | Retrieval Number: F9524038620/2020©BEIESP | DOI: 10.35940/ijrte.F9524.038620
Open Access | Ethics and Policies | Cite | Mendeley
© 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: In the field of biometrics, palmprint recognition has received great interest and made tremendous progress in the past two decades. In palmprint recognition, the important step is to extract the discriminative features from the image and compare it with templates for identification and verification tasks. In this paper, a new genetic-based 2D Gabor filter with the Convolutional Neural Network is presented. The scale and orientation details captured by Gabor filters are optimized based on central frequency, which is determined based on genetic algorithm fitness function. The proposed technique is implemented on four publicly available palmprint datasets- Poly U, CASIA, IITD, and Tongji. Experimental results confirm that the proposed technique achieves better accuracy when compared to Palmnet.
Keywords: Gabor Filter, Palmprint Recognition, CNN.
Scope of the Article: Graph Algorithms And Graph Drawing.