Finger-Vein Image Dual Contrast Adjustment and Recognition Using 2D-CNN

Authors

  • Noroz Khan Baloch Noroz Dawood University of Engineering and Technology
  • Saleem Dept. of Computer System Engg. Dawood University of Engineering and technology Karachi, Pakistan.(
  • Ramesh Dept. of Computer System Engg. Dawood University of Engineering and technology Karachi, Pakistan
  • Saqib Dept. of Telecommunication at Dawood University of Engineering and Technology Karachi, Pakistan.
  • Yawar Dept. of Electronic, NED UET Karachi, Pakistan.

DOI:

https://doi.org/10.30537/sjcms.v6i1.1001

Keywords:

Two dimensional convolutional neural network, dual contrast limited adaptive histogram equalization.

Abstract

The suggested process enhances the low contrast of the finger-vein image using dual contrast adaptive histogram equalization (DCLAHE) for visual attributes. The finger-vein histogram intensity is split out all over the image when dual CLAHE is used. For preprocessing, the finger-vein image dataset is obtained from the SDUMLA-HMT finger-vein database. Following the deployment of DCLAHE, the updated dataset is used to recognize objects using an improved 2D-CNN model. The 2D CNN model learns features by optimizing values of a preprocessed dataset. The accuracy of this model stands at 91.114%.

Downloads

Download data is not yet available.

Author Biographies

Saleem, Dept. of Computer System Engg. Dawood University of Engineering and technology Karachi, Pakistan.(

Associate Professor / Chairman.

Ramesh, Dept. of Computer System Engg. Dawood University of Engineering and technology Karachi, Pakistan

Assistant Professor.

Saqib, Dept. of Telecommunication at Dawood University of Engineering and Technology Karachi, Pakistan.

Assistant Professor/Chairman.

Yawar, Dept. of Electronic, NED UET Karachi, Pakistan.

Assistant Professor. Electronic Department, NEDUET.

Downloads

Published

2022-07-21

Issue

Vol. 6 No. 1 (2022): Vol. 6 No. 1 (2022): Sukkur IBA Journal of Computing and Mathematical Sciences-SJCMS

Section

Research Articles

License

Copyright (c) 2022 Sukkur IBA Journal of Computing and Mathematical Sciences

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The SJCMS holds the rights of all the published papers. Authors are required to transfer copyrights to journal to make sure that the paper is solely published in SJCMS, however, authors and readers can freely read, download, copy, distribute, print, search, or link to the full texts of its articles and to use them for any other lawful purpose.


The SJCMS is licensed under Creative Commons Attribution-NonCommercial 4.0 International License.