Image and video segmentation: the normalized cut framework

Author

Shi, Jianbo ; Belongie, Serge ; Leung, Thomas ; Malik, Jitendra

Author_Institution

Div. of Comput. Sci., California Inst. of Technol., Pasadena, CA, USA

Volume

1

fYear

1998

fDate

4-7 Oct 1998

Firstpage

943

Abstract

We propose a segmentation system based on the normalized cut framework proposed by Shi and Malik (see Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Juan, Puerto Rico, p.731-7, 1997). The goal is to partition the image from a big picture point of view. Perceptually significant groups are detected first while small variations and details are treated later. Different image features-intensity, color, texture, contour continuity, motion and stereo disparity are treated in one uniform framework

Keywords

edge detection; image colour analysis; image motion analysis; image segmentation; image texture; stereo image processing; video signal processing; contour continuity; image color; image features; image partitioning; image segmentation; image texture; intensity; motion disparity; normalized cut; perceptually significant groups; stereo disparity; video segmentation; Computer science; Computer vision; Detectors; Image edge detection; Image segmentation; Information filtering; Information filters; Motion segmentation; Nonlinear filters; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on

Conference_Location

Chicago, IL

Print_ISBN

0-8186-8821-1

Type

conf

DOI

10.1109/ICIP.1998.723676

Filename

723676