A parallel color algorithm for segmenting images of 3-D scenes

Abstract

Summary form only given, as follows. A parallel color algorithm for image segmentation is presented. From an input color image, the algorithm labels each pixel in the image according to the corresponding material in the scene. This segmentation is useful for many visual tasks, including inspection and object recognition. It is shown that color information is necessary to generate this kind of segmentation for a 3-D scene. The segmentation algorithm is based on a detailed analysis of the physics underlying color image formation and can be applied to images of a wide range of materials. Image texture is dealt with in a natural way. An initial edge detection on the intensity image is used to guide the color segmentation process. The algorithm is inherently parallel and can be effectively mapped onto high-performance parallel hardware. Results generated by the algorithm on several images are presented.<>