A general framework for low level vision

Nir Sochen*, Ron Kimmel, Ravikanth Malladi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish
Pages (from-to)310-318
Number of pages9
JournalIEEE Transactions on Image Processing
Issue number3
StatePublished - 1998


FundersFunder number
National Science FoundationPHY-90-21139
Office of Naval ResearchNOOO14-96-1-0381


    • Color image processing
    • Image enhancement
    • Image smoothing
    • Nonlinear image diffusion
    • Scale-space


    Dive into the research topics of 'A general framework for low level vision'. Together they form a unique fingerprint.

    Cite this