VISTO: A new CBIR system for vector images

In this paper, we present the main features of VISTO (Vector Image Serach TOol), a new Content-Based Image Retrieval (CBIR) system for vector images. Though unsuitable for photorealistic imagery, vector graphics are continually becoming more advanced and diffused. In fact, vector images are made up of individual, scalable objects defined by mathematical equations rather than pixels as in the case of raster images. This makes vector images fully scalable, resolution independent, not restricted to rectangular shape, allowing layering and editable/searchable text. Notwithstanding this increasing interest, all the CBIR systems proposed in the literature deal with raster images, while the research area concerning CBIR systems for vectorial images is quite new. To the best of our knowledge, VISTO is the first CBIR system for vector images proposed in the literature, and it has been designed for the retrieval of vector images in SVG (Scalable Vector Graphics) format. The contribution of this paper is twofold: we first describe the main characteristics of VISTO from the engine and the interface point of view, highlighting the differences with respect to CBIR systems for raster images known in the literature, and then evaluate VISTO’s engine from an experimental point of view within an advanced high quality 2D animation environment supporting cartoon episodes management.