Image Categorization Using Hierarchical Spatial Matching Kernel

Spatial pyramid matching (SPM) has been an important approach to image categorization. This method partitions the image into increasingly fine sub-regions and computes histograms of local features at each sub-region. Although SPM is an efficient extension of an unordered bag-of-features image representation, it still measures the similarity between sub-regions by application of the bag-of-features model. Therefore, it is limited in its capacity to achieve optimal matching between sets of unordered features. To overcome this limitation, we propose a hierarchical spatial matching kernel (HSMK) that uses a coarse-to-fine model for the sub-regions to obtain better optimal matching approximations. Our proposed kernel can deal robustly with unordered feature sets as well as various cardinalities. In experiments, results of HSMK outperformed those of SPM and led to state-of-the-art performance on several well-known databases of benchmarks in image categorization, even though we use only a single type of image feature.