ML Anthology

Image Compression and Reconstruction Using a 1-D Feature Catalogue

Brian Y. K. Aw, Robyn A. Owens, John Ross
ECCV 1992 pp. 749-753
doi:10.1007/3-540-55426-2_85 /eccv/1992/aw1992eccv-image/

Abstract

This paper presents a method of compressing and reconstructing a real image using its feature map and a feature catalogue that conprises of feature templates representing the local forms of features found in a number of natural images. Unlike most context-texture based techniques that assume all feature profiles at feature points to be some form of graded steps, this method is able to restore the shading in the neighbourhood of a feature point close to its original values, whilst maintaining high compression ratios of around 20∶1.

PDF ECCV Semantic Scholar

Cite

Text

Aw et al. "Image Compression and Reconstruction Using a 1-D Feature Catalogue." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_85

Markdown

[Aw et al. "Image Compression and Reconstruction Using a 1-D Feature Catalogue." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/aw1992eccv-image/) doi:10.1007/3-540-55426-2_85

BibTeX

@inproceedings{aw1992eccv-image,
  title     = {{Image Compression and Reconstruction Using a 1-D Feature Catalogue}},
  author    = {Aw, Brian Y. K. and Owens, Robyn A. and Ross, John},
  booktitle = {European Conference on Computer Vision},
  year      = {1992},
  pages     = {749-753},
  doi       = {10.1007/3-540-55426-2_85},
  url       = {https://mlanthology.org/eccv/1992/aw1992eccv-image/}
}