Efficient retrieval by shape content

We propose an approach for image similarity retrieval based on shape information. The heart of our methodology is a a dynamic programming shape matching algorithm which detects similarities between shapes at various levels of shape detail (resolution). Our method provides for indexing of a data set, achieving up to three orders of magnitude speed-up over sequential scanning. We illustrate the application of our method to real two-dimensional static hand gesture data. We also demonstrate the superiority of our approach over traditional methods of shape matching and retrieval, such as Fourier descriptors, geometric and sequential moments