An MLP-based texture segmentation method without selecting a feature set

A texture segmentation technique which employs a multilayer perceptron (MLP) and does not consider the selection of features is presented in this paper. Thus, users can avoid selection and computation of the feature set and hence real-time segmentation may be possible. The technique apparently works...

Full description

Saved in:
Bibliographic Details
Published in:Image and vision computing 1997-12, Vol.15 (12), p.937-948
Main Authors: Bhattacharya, U., Chaudhuri, B.B., Parui, S.K.
Format: Article
Language:English
Subjects:
Algorithmics. Computability. Computer arithmetics
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Feature extraction
Modified backpropagation
Multilayer perceptron
Pattern recognition. Digital image processing. Computational geometry
Texture segmentation
Theoretical computing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A texture segmentation technique which employs a multilayer perceptron (MLP) and does not consider the selection of features is presented in this paper. Thus, users can avoid selection and computation of the feature set and hence real-time segmentation may be possible. The technique apparently works in a fashion similar to our visual system whereby we do not consciously compute any feature for texture discrimination. A detailed study has been made for the selection of the network size. A newly proposed variant of the back-propagation algorithm has been used for more efficient training of the network. An edge-preserving noise-smoothing approach has been proposed to remove noise from the segmented image.
ISSN:0262-8856
1872-8138
DOI:10.1016/S0262-8856(97)00035-8