Application of planar shape comparison to object retrieval in image databases

A similarity measure for silhouettes of 2D objects is presented, and its pr operties are analyzed with respect to retrieval of similar objects in image databases. To reduce influence of digitization noise as well as segmentati on errors the shapes are simplified by a new process of digital curve evolu tion. To compute our similarity measure, we first establish the best possib le correspondence of visual parts (without explicitly computing the visual parts). Then the similarity between corresponding parts is computed and sum med. Experimental results show that our shape matching procedure gives an i ntuitive shape correspondence and is stable with respect to noise distortio ns. (C) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd . All rights reserved.