Image representation and compression via adaptive multi-Gabor representations

Shidong Li

doi:10.1117/12.330374

Translator Disclaimer

6 November 1998 Image representation and compression via adaptive multi-Gabor representations

Shidong Li

Author Affiliations +

Proceedings Volume 3456, Mathematics of Data/Image Coding, Compression, and Encryption; (1998) https://doi.org/10.1117/12.330374
Event: SPIE's International Symposium on Optical Science, Engineering, and Instrumentation, 1998, San Diego, CA, United States

Abstract

We present some initial study results on image representation and compression using multi-Gabor representations. 2D multi-Gabor representations (MGRs) are a technique of Gabor representations incorporating a set of nonseparable 2D window waveforms in a basis-like system. Windows use in a MGR can be customized to have different spatial and frequency orientations and different spatial and frequency localizations. MGRs have obvious values in efficient image representations and/or compression since an image signal typically has a variety of spatial and frequency contents and orientations. An image could also have textures of different orientations. A multi-Gabor representation that incorporates a set of windows of different localizations and orientations has a build-in adaptive potential, which can provide the most concise representation.

Citation Download Citation

Shidong Li "Image representation and compression via adaptive multi-Gabor representations", Proc. SPIE 3456, Mathematics of Data/Image Coding, Compression, and Encryption, (6 November 1998); https://doi.org/10.1117/12.330374

ACCESS THE FULL ARTICLE