Kuwait-University-Journal-of-Law-header
Search
Kuwait Journal of Science

Previous Issues

Advance Search
Year : From To Vol
Issue Discipline:
Author

Volume :34 Issue : 2 2007      Add To Cart                                                                    Download

Adaptive architecture neural nets

Auther : ROBINA ASHRAF, MUHAMMAD AKBAR AND NOMAN JAFRI

College of Signals, National University of Sciences &Technology, Pakistan.

robina0321@yahoo.com

 ABSTRACT

 

In this paper a technique is proposed for medical image compression using neural network based vector quantizers. There exist hundreds of modalities of medical images and each modality has hundreds of subclasses for different organs. In such a situation, it is difficult to generalize a neural network for all modalities. To tackle this problem and having a prior knowledge about similar nature of medical images for a single type, we propose a flag byte which is automatically set by image size and some other features. This flag byte is then used to select the size of the net and codebook. The proposed method not only leads to dynamic architectures of neural nets but also towards an adaptive selection of codebook sizes.  This method yields high compression ratios with much better quality than existing standards.

 

KEYWORDS: Image compression; Learning Vector Quantizer; Self Organizing Feature Maps        

Kuwait Journal of Science
Journal of Law

You are Visitor No.

55208

Journal of Law
Journal of Law
Tell your friendsJournal of Law
Journal of Law

Last Updated

Jun 19, 2012

Journal of Law
Journal of Law
Journal of Law

Please enter your email Here to receive our news

Journal of Law