A novel computer desktop image compression technology based on clustering algorithm
This paper proposes the new perspective on image compression algorithm with the assistance of the machine learning algorithms. Inspired from the literature review, with the continuous development of multimedia and the Internet application, and more and more high to the requirement of the image compr...
Uložené v:
| Vydané v: | RISTI : Revista Ibérica de Sistemas e Tecnologias de Informação číslo E6; s. 295 |
|---|---|
| Hlavný autor: | |
| Médium: | Journal Article |
| Jazyk: | English Portuguese |
| Vydavateľské údaje: |
Lousada
AISTI (Iberian Association for Information Systems and Technologies)
01.08.2016
Associação Ibérica de Sistemas e Tecnologias de Informacao |
| Predmet: | |
| ISSN: | 1646-9895 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Shrnutí: | This paper proposes the new perspective on image compression algorithm with the assistance of the machine learning algorithms. Inspired from the literature review, with the continuous development of multimedia and the Internet application, and more and more high to the requirement of the image compression technology, it was found that have some static image compression standard has been difficult to meet certain requirements. We therefore propose the new idea on the image compression based on the wavelet analysis and clustering model. To conduct the reasonable experiment, we solve as follows. For the color image quality measure problem, because the color perception is closely related to the human visual characteristics, on a different color and color changes in different directions, and the human eye perception of sensitivity is not the same, so that the color measurement is a complicated process. This makes the color image quality evaluation than gray image is much more difficult. In order to simple, objective for the purpose of, still color image restoration using PSNR as quality evaluation, but we will list three component of color image PSNR, respectively. The experiment proves the effectiveness of the method. Keywords: Image processing, pattern recognition, data compression, clustering algorithm, desktop image |
|---|---|
| Bibliografia: | SourceType-Scholarly Journals-1 ObjectType-General Information-1 content type line 14 |
| ISSN: | 1646-9895 |