Neural network approaches for predictive vector quantization of an image

Title:

Neural network approaches for predictive vector quantization of an image

Creator:

Mihalík, Ján and Labovský, Rostislav

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:2b8cde32-ef50-4a85-9d01-2d9016471b75
uuid:2b8cde32-ef50-4a85-9d01-2d9016471b75

Subject:

neural network, vector quantization, vector prediction, Kohonen selforganization feature maps, clustering algoritlmi, and multilayer perceptron

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

The paper deals with a predictive vector quantization of an image based on a neural network architectures, wliere a vector predictor is iniplernented by three-layer neural network with various hidden nodes and bias units, sigrnoid function as nonlinearity and where vector quantizer is inipleinented by Kohonen self-organizing feature maps, it means the codebook is obtained by neural network clustering algorithm. We have tested aíi influence of a nuinber of hidden nodes, various convergention rates of a learning algorithm and a presence of the sigrnoid function to a rnean square prediction error. Next we háve studied an influence of codebook size to a rnean sciuare quantization error, that means a performance of predictive vector quantization system for various bit rates. The image of Lena of size 512 X 512 pels was coded for various bit rates, where we háve ušed onedirnensional and two-dimensional vector prediction of the blocks of pels.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2001 Volume:11 | Number:1

Harvested from:

CDK

Metadata only:

false