Vector quantization with hierarchical classification of sub-blocks

Jorma Virtamo, Seppo Valli

Research output: Contribution to journalArticleScientificpeer-review

1 Citation (Scopus)

Abstract

A hierarchical classified vector quantization (HCVQ) method is described. In this method, the image is coded in several steps, starting with a relatively large block size, and successively dividing the block into smaller sub-blocks in a quad-tree fashion. The initial block is first vector quantized in the normal way. Classified vector quantization is then performed for its sub-blocks using the vector index of the initial block, i.e. rough information of the image, and the location of the sub-block within the initial block as classifiers. The coding proceeds in a similar way, adding more information of the fine details at each level. The method is found to be effective and to give a good subjective quality. It is also simple to implement, leading to coding speeds typical to a tree search VQ.
Original languageEnglish
Pages (from-to)475-479
JournalSignal Processing: Image Communication
Volume8
Issue number6
DOIs
Publication statusPublished - Sep 1996
MoE publication typeA1 Journal article-refereed

Fingerprint

Vector quantization
Classifiers

Keywords

  • image coding
  • vector quantization
  • multiresolution
  • hierarchical

Cite this

@article{f5a24e3cd7ca4e54af83d8b9f350f07d,
title = "Vector quantization with hierarchical classification of sub-blocks",
abstract = "A hierarchical classified vector quantization (HCVQ) method is described. In this method, the image is coded in several steps, starting with a relatively large block size, and successively dividing the block into smaller sub-blocks in a quad-tree fashion. The initial block is first vector quantized in the normal way. Classified vector quantization is then performed for its sub-blocks using the vector index of the initial block, i.e. rough information of the image, and the location of the sub-block within the initial block as classifiers. The coding proceeds in a similar way, adding more information of the fine details at each level. The method is found to be effective and to give a good subjective quality. It is also simple to implement, leading to coding speeds typical to a tree search VQ.",
keywords = "image coding, vector quantization, multiresolution, hierarchical",
author = "Jorma Virtamo and Seppo Valli",
year = "1996",
month = "9",
doi = "10.1016/0923-5965(95)00066-6",
language = "English",
volume = "8",
pages = "475--479",
journal = "Signal Processing: Image Communication",
issn = "0923-5965",
publisher = "Elsevier",
number = "6",

}

Vector quantization with hierarchical classification of sub-blocks. / Virtamo, Jorma; Valli, Seppo.

In: Signal Processing: Image Communication, Vol. 8, No. 6, 09.1996, p. 475-479.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Vector quantization with hierarchical classification of sub-blocks

AU - Virtamo, Jorma

AU - Valli, Seppo

PY - 1996/9

Y1 - 1996/9

N2 - A hierarchical classified vector quantization (HCVQ) method is described. In this method, the image is coded in several steps, starting with a relatively large block size, and successively dividing the block into smaller sub-blocks in a quad-tree fashion. The initial block is first vector quantized in the normal way. Classified vector quantization is then performed for its sub-blocks using the vector index of the initial block, i.e. rough information of the image, and the location of the sub-block within the initial block as classifiers. The coding proceeds in a similar way, adding more information of the fine details at each level. The method is found to be effective and to give a good subjective quality. It is also simple to implement, leading to coding speeds typical to a tree search VQ.

AB - A hierarchical classified vector quantization (HCVQ) method is described. In this method, the image is coded in several steps, starting with a relatively large block size, and successively dividing the block into smaller sub-blocks in a quad-tree fashion. The initial block is first vector quantized in the normal way. Classified vector quantization is then performed for its sub-blocks using the vector index of the initial block, i.e. rough information of the image, and the location of the sub-block within the initial block as classifiers. The coding proceeds in a similar way, adding more information of the fine details at each level. The method is found to be effective and to give a good subjective quality. It is also simple to implement, leading to coding speeds typical to a tree search VQ.

KW - image coding

KW - vector quantization

KW - multiresolution

KW - hierarchical

U2 - 10.1016/0923-5965(95)00066-6

DO - 10.1016/0923-5965(95)00066-6

M3 - Article

VL - 8

SP - 475

EP - 479

JO - Signal Processing: Image Communication

JF - Signal Processing: Image Communication

SN - 0923-5965

IS - 6

ER -