Title :
Probability models for clutter in natural images
Author :
Grenander, Ulf ; Srivastava, Anuj
Author_Institution :
Div. of Appl. Math., Brown Univ., Providence, RI, USA
fDate :
4/1/2001 12:00:00 AM
Abstract :
We propose a framework for modeling clutter in natural images. Assuming that: 1) images are made up of 2D (projected) views of 3D (real) objects and 2) certain simplifying conditions hold, we derive an analytical density for natural images. This expression is shown to match well with the observed densities (histograms). In addition to deriving multidimensional densities, several extensions are also proposed
Keywords :
computer vision; object recognition; probability; 2D projected views; 3D real objects; analytical density; clutter; multidimensional densities; natural images; probability models; Context modeling; Face detection; Image edge detection; Image recognition; Image texture analysis; Object recognition; Performance analysis; Pixel; Probability; Shape;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
