Early vision processing using a multi-stage diffusion process

TitleEarly vision processing using a multi-stage diffusion process
Publication TypeConference Papers
Year of Publication1993
AuthorsYacoob Y, Davis LS
Conference Name1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93
Date Published1993/06//
ISBN Number0-8186-3880-X
Keywords3-D space, Computational modeling, Computer vision, Diffusion processes, discontinuity detection, early vision processing, Educational institutions, Image edge detection, Image segmentation, Laboratories, multistage diffusion process, Noise shaping, noise-free edges, noisy edges, Performance analysis, roof edges, segmentation, SHAPE, shape homogeneous regions, step edges, valley edges

The use of a multistage diffusion process in the early processing of range data is examined. The input range data are interpreted as occupying a volume in 3-D space. Each diffusion stage simulates the process of diffusing part of the boundary of the volume into the volume. The outcome of the process can be used for both discontinuity detection and segmentation into shape homogeneous regions. The process is applied to synthetic noise-free and noisy step, roof, and valley edges as well as to real range images