A commonly used representation of a visual pattern is the set of marginal probability distributions of the output of a bank of filters (Gaussian, Laplacian, Gabor etc.). This representation has been used effectively for a variety of vision tasks including texture classification, texture synthesis, object detection and image retrieval. We examine the ability of this representation to discriminate between an arbitrary pair of visual stimuli. Examples of patterns are derived that provably possess the same marginal statistical properties, yet are "visually distinct." These results suggest the need for either employing a large and diverse filter bank or incorporating joint statistics in order to represent a large class of visual patterns.
On the use of marginal statistics of subband images
2003-01-01
502848 byte
Conference paper
Electronic Resource
English
On the Use of Marginal Statistics of Subband Images
British Library Conference Proceedings | 2003
|Subband-Transform MATLAB Functions for Processing Images
Online Contents | 1995
Optimum Classification in Subband Coding of Images
British Library Conference Proceedings | 1994
|Subband/Transform MATLAB Functions For Processing Images
NTRS | 1995
|