Application of SVM Classifier in IR Target Recognition

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 over-fitting 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.