Region-based shape representation and similarity measure suitable for content-based image retrieval

A region-based approach to shape representation and similarity measure is p resented. The shape representation is invariant to translation, scale and r otation. The similarity measure conforms to human similarity perception, i. e., perceptually similar shapes have high similarity measure. An experiment al shape retrieval system has been developed and its performance has been s tudied. The shape retrieval performance of the proposed approach is better than that of the more established Fourier descriptor method.