SNN clustering kernel technique for content-based scene matching

In this paper, the radial basis vector (RBV) is proposed to describe the descriptor set of an image. And the shared nearest neighbor clustering kernel (SNNCK) technique is proposed to match RBV pairs. SNNCK is based on the charge attractive model, which will make the unequal-dimensional data sets clustering naturally. Thus, this novel algorithm is able to match the unequal-dimensional data sets when the number of descriptors of two images are unequal. It also can automatically extract the repetition pattern of the reference date set, which is helpful to avoid the wrong matching. Experimental results are also provided, and these results demonstrate superior performances of SNNCK algorithm by using the feature point sets with strong disturbs.