Clustering with K-Harmonic means applied to colour image quantization

Mariusz Fra̧ckiewicz; Henryk Palus

doi:10.1109/ISSPIT.2008.4775684

Clustering with K-Harmonic means applied to colour image quantization

Department of Data Science and Engineering (RAU/RAU4)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Citations (Scopus)

Abstract

The main goal of colour quantization methods is a colour reduction with minimum colour error. In this paper were investigated six following colour quantization techniques: the classical median cut, improved median cut, clustering k-means technique in two colour versions (RGB, CIELAB) and also two versions of relative novel technique named k-harmonic means. The comparison presented here was based on testing of ten natural colour images for quantization into 16, 64 and 256 colours. In evaluation process two criteria were used: the mean squared quantization error (MSE) and the average error in the CIELAB colour space (AE). During tests the efficiency of k-harmonic means applied to colour quantization has been proved.

Original language	English
Title of host publication	Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008
Pages	52-57
Number of pages	6
DOIs	https://doi.org/10.1109/ISSPIT.2008.4775684
Publication status	Published - 2008
Event	8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008 - Sarajevo, Bosnia and Herzegovina Duration: 16 Dec 2008 → 19 Dec 2008

Publication series

Name	Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008

Conference

Conference	8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008
Country/Territory	Bosnia and Herzegovina
City	Sarajevo
Period	16/12/08 → 19/12/08

Keywords

Colour image quantization, Clustering, K-means, K-harmonic means, Quality measures

ASJC Scopus subject areas

Information Systems
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ISSPIT.2008.4775684

Cite this

Fra̧ckiewicz, M., & Palus, H. (2008). Clustering with K-Harmonic means applied to colour image quantization. In Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008 (pp. 52-57). Article 4775684 (Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008). https://doi.org/10.1109/ISSPIT.2008.4775684

@inproceedings{f22331a22f1343aaa898a771df2b564c,

title = "Clustering with K-Harmonic means applied to colour image quantization",

abstract = "The main goal of colour quantization methods is a colour reduction with minimum colour error. In this paper were investigated six following colour quantization techniques: the classical median cut, improved median cut, clustering k-means technique in two colour versions (RGB, CIELAB) and also two versions of relative novel technique named k-harmonic means. The comparison presented here was based on testing of ten natural colour images for quantization into 16, 64 and 256 colours. In evaluation process two criteria were used: the mean squared quantization error (MSE) and the average error in the CIELAB colour space (AE). During tests the efficiency of k-harmonic means applied to colour quantization has been proved.",

keywords = "Colour image quantization, Clustering, K-means, K-harmonic means, Quality measures",

author = "Mariusz Fr{\c a}ckiewicz and Henryk Palus",

year = "2008",

doi = "10.1109/ISSPIT.2008.4775684",

language = "English",

isbn = "9781424435555",

series = "Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008",

pages = "52--57",

booktitle = "Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008",

note = "8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008 ; Conference date: 16-12-2008 Through 19-12-2008",

}

Fra̧ckiewicz, M & Palus, H 2008, Clustering with K-Harmonic means applied to colour image quantization. in Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008., 4775684, Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008, pp. 52-57, 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008, Sarajevo, Bosnia and Herzegovina, 16/12/08. https://doi.org/10.1109/ISSPIT.2008.4775684

Clustering with K-Harmonic means applied to colour image quantization. / Fra̧ckiewicz, Mariusz ; Palus, Henryk.
Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008. 2008. p. 52-57 4775684 (Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Clustering with K-Harmonic means applied to colour image quantization

AU - Fra̧ckiewicz, Mariusz

AU - Palus, Henryk

PY - 2008

Y1 - 2008

N2 - The main goal of colour quantization methods is a colour reduction with minimum colour error. In this paper were investigated six following colour quantization techniques: the classical median cut, improved median cut, clustering k-means technique in two colour versions (RGB, CIELAB) and also two versions of relative novel technique named k-harmonic means. The comparison presented here was based on testing of ten natural colour images for quantization into 16, 64 and 256 colours. In evaluation process two criteria were used: the mean squared quantization error (MSE) and the average error in the CIELAB colour space (AE). During tests the efficiency of k-harmonic means applied to colour quantization has been proved.

AB - The main goal of colour quantization methods is a colour reduction with minimum colour error. In this paper were investigated six following colour quantization techniques: the classical median cut, improved median cut, clustering k-means technique in two colour versions (RGB, CIELAB) and also two versions of relative novel technique named k-harmonic means. The comparison presented here was based on testing of ten natural colour images for quantization into 16, 64 and 256 colours. In evaluation process two criteria were used: the mean squared quantization error (MSE) and the average error in the CIELAB colour space (AE). During tests the efficiency of k-harmonic means applied to colour quantization has been proved.

KW - Colour image quantization, Clustering, K-means, K-harmonic means, Quality measures

UR - https://www.scopus.com/pages/publications/67649861657

U2 - 10.1109/ISSPIT.2008.4775684

DO - 10.1109/ISSPIT.2008.4775684

M3 - Conference contribution

AN - SCOPUS:67649861657

SN - 9781424435555

T3 - Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008

SP - 52

EP - 57

BT - Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008

T2 - 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008

Y2 - 16 December 2008 through 19 December 2008

ER -

Fra̧ckiewicz M , Palus H. Clustering with K-Harmonic means applied to colour image quantization. In Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008. 2008. p. 52-57. 4775684. (Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008). doi: 10.1109/ISSPIT.2008.4775684

Clustering with K-Harmonic means applied to colour image quantization

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this