A network for multiscale image segmentation

Author

Perona, Pietro ; Malik, Jitendra

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA

fYear

1988

fDate

7-9 Jun 1988

Firstpage

2565

Abstract

Detecting edges of objects in their images is a basic problem in computational vision. The authors present the major ideas behind the use of scale space and anisotropic diffusion for edge detection, show that anisotropic diffusion can enhance edges, suggest a network implementation of anisotropic diffusion, and provide design criteria for obtaining networks performing scale space and edge detection. The results of a software implementation are shown

Keywords

computer vision; computerised pattern recognition; picture processing; anisotropic diffusion; computational vision; design criteria; edge detection; multiscale image segmentation; network implementation; picture processing; scale space; software implementation; Artificial intelligence; Filtering; Gaussian processes; Image edge detection; Image resolution; Image segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1988., IEEE International Symposium on

Conference_Location

Espoo

Type

conf

DOI

10.1109/ISCAS.1988.15465

Filename

15465

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2606834