Image Compression using an Enhanced Self Organizing Map Algorithm with Vigilance Parameter

In this paper, a new approach for image compression is presented. The enhanced SOM algorithm applies a vigilance parameter in order to test if the maximum value of all activation functions in each training step exceeds the minimum threshold. If vigilance test is not passed, a new cluster will be add...

Full description

Saved in:
Bibliographic Details
Main Authors: Bavafa, E., Yazdanpanah, M.J.
Format: Conference Proceeding
Language:English
Subjects:
Clustering algorithms
Color
Computational complexity
Image coding
Image processing
Lattices
Neurons
Organizing
Process control
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a new approach for image compression is presented. The enhanced SOM algorithm applies a vigilance parameter in order to test if the maximum value of all activation functions in each training step exceeds the minimum threshold. If vigilance test is not passed, a new cluster will be added to the network; else the winner cluster will be updated. Therefore, the network could be extendable due to pattern distribution. The proposed approach is compared with ART1. The performance of enhanced SOM algorithm does not depend on the input presentation order. As observed through simulations, the new algorithm with vigilance parameter reduces the computational complexity, and presents better quality compared with Kohonen's SOM.
ISSN:2161-4393
2161-4407
DOI:10.1109/IJCNN.2006.246787