A general framework for low level vision

DMCA

A general framework for low level vision (1998)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Nir Sochen , Ron Kimmel , Ravikanth Malladi

Venue:	IEEE TRANS. ON IMAGE PROCESSING
Citations:	216 - 37 self

BibTeX

@ARTICLE{Sochen98ageneral,
    author = {Nir Sochen and Ron Kimmel and Ravikanth Malladi},
    title = {A general framework for low level vision},
    journal = {IEEE TRANS. ON IMAGE PROCESSING},
    year = {1998},
    pages = {310--318}
}

OpenURL

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 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.

Keyphrases

low level vision geometrical framework natural flow image enhancement image smoothing powerful denoising 2-d surface intensity image efficient scheme simple scaling index term color image processing nonlinear image diffusion color image gray-level image image scale space new geometrical framework multidimensional signal scale space algorithm intensity contrast

DMCA