A vector coding method for natural images

Reiko Osada, Terumasa Aoki, Hiroshi Yasuda

Research output: Chapter in Book/Report/Conference proceedingConference contribution


A new vector coding for natural image, which has a compressive algorithm, is presented and images' features showed in this method are described. In this paper, the pixel-value-boundary contours on RGB or YCrCb planes of natural images are expressed by function approximation and then their contour shapes are predicted from similar contours in the decoder side. The proposed vector coding method has two main merits: the one is to meet the demands of expansion and reduction of images, the second is to suit content distribution because images can be kept their quality even under the repetition of editing. These are due to representation of function approximation. In spite of these merits on vector coding, any applications to natural have never been studied for its considerably increase of data. To put vector coding for natural images to practical use, we try to compress the data by using characteristics in three-dimensional representation of images.

Original languageEnglish
Title of host publicationProceedings - Applied Imagery Pattern Recognition Workshop
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Print)0769509789
Publication statusPublished - 2000
Externally publishedYes
Event29th Applied Imagery Pattern Recognition Workshop, AIPR 2000 - Washington, United States
Duration: 2000 Oct 162000 Oct 18


Other29th Applied Imagery Pattern Recognition Workshop, AIPR 2000
Country/TerritoryUnited States

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'A vector coding method for natural images'. Together they form a unique fingerprint.

Cite this