Underwater image recognition is a very challenging task. To overcome the problems of small sample size and poor image quality, we propose a new deep support vector machine (DSVM) algorithm. The method reduced the feature dimensions and eliminated noise. Moreover, the different kernel functions in the network ensemble are conducive to adapting to the feature distribution of multiple types of targets. In this paper, we firstly proposed a new DSVM network. Then, we use ensemble and “one-to-one”(O-v-O) method to achieve multi-classification. Finally, to evaluate the effectiveness of the proposed method, we conducted verification experiments on three data sets. The experimental results show that the proposed DSVM algorithm can effectively avoid over-fitting and improve the recognition rate in the recognition of multiple types of underwater target images.
Multi-class Underwater Image Recognition Based on DSVM
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 140 ; 1398-1408
2022-03-18
11 pages
Article/Chapter (Book)
Electronic Resource
English
Autonomous line patrol underwater robot system based on image recognition
European Patent Office | 2022
|Image recognition rescue system of small underwater unmanned ship
European Patent Office | 2023
|3-D underwater object recognition
Tema Archive | 2002
|Multi-class relevance feedback content-based image retrieval
British Library Online Contents | 2003
|