A general framework for low level vision

Author

Sochen, Nir ; Kimmel, Ron ; Malladi, Ravikanth

Volume

7

Issue

3

fYear

1998

fDate

3/1/1998 12:00:00 AM

Firstpage

310

Lastpage

318

Abstract

We introduce a new geometrical framework based on which natural flows for image scale space and enhancement are presented. We consider intensity images as surfaces in the (x,I) space. The image is, thereby, a two-dimensional (2-D) surface in three-dimensional (3-D) space for gray-level images, and 2-D surfaces in five dimensions for color images. The new formulation unifies many classical schemes and algorithms via a simple scaling of the intensity contrast, and results in new and efficient schemes. Extensions to multidimensional signals become natural and lead to powerful denoising and scale space algorithms

Keywords

computer vision; edge detection; image colour analysis; image enhancement; image segmentation; smoothing methods; 2D surface; 3D space; color images; computer vision; denoising algorithms; geometrical framework; gray-level images; image enhancement; image flow; image scale space; image segmentation; image smoothing; intensity contrast scaling; intensity images; low level vision; multidimensional signals; nonlinear diffusion algorithm; scale space algorithms; Color; Computer vision; Detectors; Image edge detection; Image enhancement; Laboratories; Mathematics; Noise reduction; Physics; Two dimensional displays;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/83.661181

Filename

661181