Abstract
Because of the accuracy requirement of a target recognition system, a target recognition algorithm based on support vector machine is proposed. Then the automatic target recognition system based on SVM, methods of the target feature extraction and the parameter optimization of the SVM classifier are introduced. The experimental results show that the algorithm given can effectively detect and recognize the image target and possess the preferable properties of counter-complex background.
Original language | English |
---|---|
Pages (from-to) | 791-793+798 |
Journal | Guangxue Jishu/Optical Technique |
Volume | 34 |
Issue number | 5 |
Publication status | Published - Sept 2008 |
Keywords
- Feature extraction
- SVM
- Target recognition