Application of SVM classifier in IR target recognition

摘要：

In the paper, support vector machine is proposed in IR target recognition. Grid method is used to select the appropriate parameters of SVM to avoid overfitting due to the choice of inappropriate parameters. We employ coal mine IR monitoring images to testify the IR target recognition ability of SVM. And features and category of the coal mine IR monitoring images are given. The experimental results illustrate that the IR target recognition accuracy of SVM is 100％.Thus, SVM is an excellent IR target recognition method.

关键词： SVM classifier IR target recognition monitoring images

作者: Feng Wen-ge

作者单位: Department of Electronic & Information Engineering Hebi Vocational Technical College Hebi 458030,China

会议类型: 国际会议

会议名称: 2010 4th International Conference on Intelligent Information Techonlogy Application(第四届智能信息技术应用国际学术研讨会 IITA 2010)

会议地点: 秦皇岛

会议语种:英文

页码: 196-199

在线出版日期: 2010-11-05（万方平台首次上网日期，不代表论文的发表时间）