Sea target detection based on SVM method using HSV color space

Sea target detection is an important goal for military purposes and navigation. A new supervised clustering method is introduced for optimum classification which is based on the Support Vector Machine (SVM) classifier. Utilizing color features for sea target detection was not considered seriously in previous works. In this paper, the SVM is utilized for classification and color features are applied to train this classifier. For obtaining the best results, the training samples are extracted from the HSV color space. The superiority of the new method to the relative previous works is conspicuous.