文摘
A qualitative, volumetric part-based model is proposed to improve the categorical invariance and viewpoint invariance in content-based image retrieval, and a novel two-step part-categorization method is presented to build it. The method consists first in transforming parts extracted from a segmented contour primitive map and then categorizing the transformed parts using interpretation rules. The first step allows noisy extracted parts to be transformed to the domain of a simple classifier. The second step computes features of the transformed parts for categorization. Content-based image retrieval experiments using real images of complex multi-part objects confirm that a model built from the categorized parts improves both the categorical invariance and the viewpoint invariance. It does so by directly addressing the fundamental limits of low-level models.