Photo Photo Photo Photo Photo Photo

Print
E-mail
Computer Science: Image Labeling Using Hopfield Neural NE

 

Image Labeling Using Hopfield Neural NE

Reyahd S. Nauom, Riyadh A. Mehdi* & Lubna R. Hussian

Department of Computer Science, College of Science. University of Baghdad. Baghdad-Iraq * Department of Computer Science, College of Science, Nahreen University. Baghdad-lraq,

Abstract

This paper considers the application of neural networks to the problem of image labeling. It is assumed that an image has been segmented into regions and that predefined uniary properties as well as binary relationships between these regions have been extracted from the segmented image. It is also assumed that the know ledge base of object models contains corresponding unary features of object models. A Hopfield optimization network is used as a matching mechanism based on an energy function that compute the hamming distance between tow neurons (nodes) based on the consistency between object models and image regions with regard to the unary and binary constraints. A node represents an association between an image region with one of the possible labels. The results presented in this paper indicate validity of the neural approach and the corresponding energy function used.


alt

 

 

S5 Box

Login



Register

*
*
*
*
*

Fields marked with an asterisk (*) are required.