Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Visual texture segmentation based on energy measures

Open Access Open Access

Abstract

Various attempts have been made to describe the human ability to use texture information to define perceptual regions. Some of these have used statistical measures of structure while others have been based on differences in occurrence of certain features. We have tried a very simple approach based on the local energy present in concentric and oriented linear receptive fields. Measures of this kind can account for a number of observed phenomena: (1) In a texture made up of randomly oriented L and + shaped elements, strong segregation is ob­served if the line segments forming the elements are of the same length. If the + elements are enlarged slightly (10–20%), the segregation be­comes much weaker. (2) If the size of the elements in a texture is reduced while the average spacing between them is kept constant, the segregation also becomes weaker.

© 1986 Optical Society of America

PDF Article
More Like This
Visual texture segmentation based on oriented energy pyramids

James R. Bergen
FD1 OSA Annual Meeting (FIO) 1988

Gabor functions and textural segmentation

Mark R. Turner
WJ38 OSA Annual Meeting (FIO) 1985

Segmentation of Textured Images

Allan G. Weber and Alexander A. Sawchuk
FB1 Machine Vision (MV) 1985

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.