Shape retrieval based on dynamic programming

We propose a shape matching algorithm for deformed shapes based on dynamic programming. Our algorithm is capable of grouping together segments at finer scales in order to come up with appropriate correspondences with segments at coarser scales. We illustrate the effectiveness of our algorithm in retrieval of shapes by content on two different two-dimensional (2-D) datasets, one of static hand gesture shapes and another of marine life shapes. We also demonstrate the superiority of our approach over traditional approaches to shape matching and retrieval, such as Fourier descriptors and geometric and sequential moments. Our evaluation is based on human relevance judgments following a well-established methodology from the information retrieval field.