Rapid Automated Polygonal Image Decomposition

Abstract

We present RaveGrid, a software that efficiently converts a raster image to a scalable vector image comprised of polygons whose boundaries conform to the edges in the image. The resulting vector image has good visual quality and fidelity and can be displayed at various sizes and on various display screen resolutions. The software can render vector images in the SVG (scalable vector graphics) format or in EPS (Encapsulated Postscript). The ubiquity of image data in graphics, on the Web, and in communications, as well as the wide range of devices, from big screen TVs to hand-held cellular phones that support image display, calls for a scalable and more manipulable representation of imagery. Moreover, with the growing need for automating image-based search, object recognition, and image understanding, it is desirable to represent image content at a semantically higher level by means of tokens that support computer vision tasks.