Document Detail

On testing trained vector quantizer codebooks.
MedLine Citation:
PMID:  18282935     Owner:  NLM     Status:  In-Data-Review    
This paper discusses a criterion for testing a vector quantizer (VQ) codebook that is obtained by "training". When a VQ codebook is designed by a clustering algorithm using a training set, "time-average" distortion, which is called the training-set-distortion (TSD), is usually calculated in each iteration of the algorithm, since the input probability function is unknown in general and cumbersome to deal with. The algorithm stops when the TSD ceases to significantly decrease. In order to test the resultant codebook, validating-set-distortion (VSD) is calculated on a separate validating set (VS). Codebooks that yield small difference between the TSD and the VSD are regarded as good ones. However, the difference VSD-TSD is not necessarily a desirable criterion for testing a trained codebook unless certain conditions are satisfied. A condition that is previously assumed to be important is that the VS has to be quite large to well approximate the source distribution. This condition implies greater computational burden of testing a codebook. In this paper, we first discuss the condition under which the difference VSD-TSD is a meaningful codebook testing criterion. Then, convergence properties of the VSD, a time-average quantity, are investigated. Finally we show that for large codebooks, a VS size as small as the size of the codebook is sufficient to evaluate the VSD. This paper consequently presents a simple method to test trained codebooks for VQ's. Experimental results on synthetic data and real images supporting the analysis are also provided and discussed.
D S Kim; T Kim; S U Lee
Related Documents :
17940325 - The crystallographic fast fourier transform. recursive symmetry reduction.
14686595 - Analytical guide wire motion algorithm for simulation of endovascular interventions.
630015 - Analysis of a cooperative stereo algorithm.
22564195 - Muscle wasting in animal models of severe illness.
19440405 - Application of bayesian methods to exposure assessment of area concentrations at a rubb...
25345425 - Organisational factors of occupational accidents with movement disturbance (oamd) and p...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  IEEE transactions on image processing : a publication of the IEEE Signal Processing Society     Volume:  6     ISSN:  1057-7149     ISO Abbreviation:  IEEE Trans Image Process     Publication Date:  1997  
Date Detail:
Created Date:  2008-02-19     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9886191     Medline TA:  IEEE Trans Image Process     Country:  United States    
Other Details:
Languages:  eng     Pagination:  398-406     Citation Subset:  -    
Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Enhanced detectability of small objects in correlated clutter using an improved 2-D adaptive lattice...
Next Document:  A new approach for subset 2-D AR model identification for describing textures.