Share Email Print

Proceedings Paper

Underwater target recognition algorithm under the influence of non-uniform illumination
Author(s): Xiawei Guan; Yaohua Zhao; Yuyao He; Baoqi Li; Xuyang Chen
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Aiming at the problem of low accuracy of underwater target recognition due to the introduction of non-uniform illumination during underwater optical detection, this paper proposes an underwater target recognition algorithm under the influence of non-uniform illumination. The algorithm firstly uses the illumination invariant extraction algorithm based on Nonsubsampled Contourlet Transform (NSCT) to extract the essential features of underwater images. Then, the extracted underwater image is used as the input of the Convolutional Neural Network (CNN) to perform target recognition. The experimental results show that the recognition accuracy of the underwater target is 9% higher than the source image, reaching 96%.

Paper Details

Date Published: 12 December 2018
PDF: 8 pages
Proc. SPIE 10850, Ocean Optics and Information Technology, 108500G (12 December 2018); doi: 10.1117/12.2505299
Show Author Affiliations
Xiawei Guan, Wuhan Second Ship Design and Research Institute (China)
Yaohua Zhao, Northwestern Polytechnical Univ. (China)
Yuyao He, Northwestern Polytechnical Univ. (China)
Baoqi Li, Northwestern Polytechnical Univ. (China)
Xuyang Chen, Northwestern Polytechnical Univ. (China)

Published in SPIE Proceedings Vol. 10850:
Ocean Optics and Information Technology
Xuelong Li; Lixin Wu; Jianquan Yao; Hao Yin; Renhe Zhang; Zhongliang Zhu, Editor(s)

© SPIE. Terms of Use
Back to Top