Daramola, S. A. and Omololu, Olumide (2016) Fish Classification Algorithm using Single Value Decomposition. International Journal of Innovative Research in Science, Engineering and Technology, 5 (2). pp. 1621-1626. ISSN (Online): 2319-8753 (Print) : 2347-6710
![[img]](http://eprints.covenantuniversity.edu.ng/style/images/fileicons/application_pdf.png) |
PDF
Download (3MB) |
Abstract
Automatic fish classification system plays a very useful role in the process of separating fishes into species for human consumption,ornamentation and other usages. Manual classificationof fishes into different types is difficult and boring. This work proposes a fast and accurate system capable of classifying fish images into distinct classes based on their physical form. The system comprises image-processing, feature extraction and classification method. Fishfeature vector is obtained from Single Value Decomposition (SVD) product extracted from fish block images. Training and testing of the proposed fish classification system are done using Artificial Neural Network (ANN). Experimental test was carried out to determine the species of query fish images. Thirty-six fish images were tested, 94% correct classification result is recorded.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Fish, Single Value Decomposition, Feature vector, Artificial Neural Network. |
| Subjects: | T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science |
| Depositing User: | Mrs Hannah Akinwumi |
| Date Deposited: | 13 Apr 2016 13:02 |
| Last Modified: | 13 Apr 2016 13:02 |
| URI: | http://eprints.covenantuniversity.edu.ng/id/eprint/6546 |
Actions (login required)
 |
View Item |
