Palm Vein Recognition using SVM and CNN: A Comparative Performance Investigation

Show simple item record

dc.contributor.author Marattukalam, F
dc.contributor.author Abdulla, Waleed
dc.contributor.author Swain, Akshya
dc.contributor.author R Wanigasekara Mudiyanse Ralahamillage, Chathura
dc.contributor.author James, J
dc.date.accessioned 2021-06-08T23:36:49Z
dc.date.available 2021-06-08T23:36:49Z
dc.date.issued 2021-7-26
dc.identifier.citation In Transactions on Computational Science & Computational Intelligence. Springer Nature 26 Jul 2021
dc.identifier.uri https://hdl.handle.net/2292/55255
dc.description.abstract This study carries out a comparative investigation on the classification performance of Support Vector Machine (SVM) and Convolutional Neural Networks (CNN) for palm vein recognition. A relatively small dataset was used to reduce the computational complexity associated with SVM. The investigation is carried out considering the HK PolyU Multispectral palm vein database using samples from 25 people, each with 12 images. Many studies on palm vein recognition use CNN and SVM as approaches for recognition. But studies till date have not done a comparative evaluation of the two approaches. The results of the study demonstrate that the performance of CNN is superior compared to SVM where the CNN yields 91.7\% recognition accuracy compared to 82.4\% with SVM. The average precision and recall value for best case of SVM is 0.82 whereas for CNN is 0.92. It is seen that the precision and recall values often reach the ideal value of unity in case of CNN. The results, therefore, suggest that it is possible to get better classification accuracy with CNN from small size of training data and hence more suitable to be applied in palm vein recognition systems.
dc.publisher Springer Nature
dc.relation.ispartof Transactions on Computational Science & Computational Intelligence
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher.
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm
dc.rights.uri https://www.springer.com/gp/open-access/publication-policies/self-archiving-policy
dc.title Palm Vein Recognition using SVM and CNN: A Comparative Performance Investigation
dc.type Book Item
dc.date.updated 2021-05-21T11:14:28Z
dc.rights.holder Copyright: Springer Nature en
dc.rights.accessrights http://purl.org/eprint/accessRights/RetrictedAccess en
pubs.elements-id 853323


Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record

Share

Search ResearchSpace


Browse

Statistics