New methods of H-SVMs for the classification of multi-spectral remote sensing imagery

Through systematically analysises of existing multi-class SVMs (M-SVMs) methods, it is shown that hierarchy multi-class SVMs (H-SVMs) can be relatively effective. Further analysis shown that existing methods that measure separability between different classes are not suitable for kernel feature space. A new method is presented for separability measure in feature space based on the characters of RBF kernel function and SVMs. Based on the new separability measure, two kinds of H-SVMs, Binary Tree SVMs (BT SVMs) and Single Layer Clustering SVMs (SLC SVMs) are presented. They are both implements of following ideal: the higher a pair of two sub-classes is in the hierarchy, the easier to separate them. In this way, we can not only achieve classification accuracy by alleviate error accumulation from top to bottom, but also rise classification speed by reduce support vectors in classifier. Experimental results justify the rationality of the new separability measure and effectiveness of BT SVMs and SLC SVMs.