Shape Description for Content-based Image Retrieval E. Ardizzone 12 , A. Chella 12 , and R. Pirrone 12 1 DIAI - University of Palermo, Viale delle Scienze 90128 Palermo, Italy 2 CERE - National Research Council, Viale delle Scienze 90128 Palermo, Italy {ardizzon, chella, pirrone}@unipa.it Abstract. The present work is focused on a global image characteri- zation based on a description of the 2D displacements of the different shapes present in the image, which can be employed for CBIR applica- tions. To this aim, a recognition system has been developed, that detects au- tomatically image ROIs containing single objects, and classifies them as belonging to a particular class of shapes. In our approach we make use of the eigenvalues of the covariance matrix computed from the pixel rows of a single ROI. These quantities are ar- rangedinavectorform,andareclassifiedusingSupportVectorMachines (SVMs). The selected feature allows us to recognize shapes in a robust fashion, despite rotations or scaling, and, to some extent, independently from the light conditions. Theoretical foundations of the approach are presented in the paper, to- gether with an outline of the system, and some preliminary experimental results. 1 Introduction Images indexing and retrieval using content has gained increasing importance during last years. Almost all kinds of image analysis techniques have been in- vestigated in order to derive sets of meaningful features which could be useful for the description of pictorial information, and a considerable effort has been spent towards the development of powerful but easy-to-use commercial database engines. The most popular CBIR (content-based image retrieval) systems developed so far, like QBIC [5,7] Photobook [9], Virage [8], model the image content as a set of uncorrelated shape, texture and color features. Queries are obtained either by manual specification of the weights for each feature or by presenting an example to the system, and they’re refined by means of various relevance feedback strategies. A more effective way to describe image content is to derive global descriptions of the objects, like in the approach followed by Malik et al. [2,3]. In this way it’s possible to obtain image indexing structures that are closer to the intuitive