摘要
基于对目标识别精确性的要求,提出了基于支持向量机的自动目标识别算法。介绍了基于支持向量机的自动目标识别系统的组成和识别流程,实现了目标的特征提取、SVM分类器的参数寻优,并将优化的SVM模型应用于未知图像的目标识别中。实验表明,该方法识别效果良好,具有较好的抗复杂背景的能力。
Because of the accuracy requirement of a target recognition system, a target recognition algorithm based on sup- port 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.
出处
《光学技术》
EI
CAS
CSCD
北大核心
2008年第5期791-793,798,共4页
Optical Technique
