Authors:
Enrique Pelayo
;
David Buldain
and
Carlos Orrite
Affiliation:
University of Zaragoza, Spain
Keyword(s):
Image Compression, Competitive Learning, Neural Networks, Saliency, Self Organizing Maps, JPEG, DCT.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Image Processing and Artificial Vision Applications
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Supervised and Unsupervised Learning
;
Theory and Methods
Abstract:
This paper introduces the Magnitude Sensitive Competitive Learning (MSCL) algorithm as a reliable and effi-
cient approach for selective image compression. MSCL is a neural network that has the property of distributing
the unit centroids in certain data-distribution zones according to a target magnitude locally calculated for every
unit. This feature can be used for image compression to define the block images that will be compressed by
Vector Quantization in a later step. As a result, areas of interest receive a lower compression than other parts
in the image. Following this approach higher quality in the salient areas of a compressed image is achieved in
relation to other methods.