Publication detail

Parallel Wavelet Schemes for Images

BAŘINA, D. KULA, M. ZEMČÍK, P.

Original Title

Parallel Wavelet Schemes for Images

Type

journal article in Web of Science

Language

English

Original Abstract

In this paper, we introduce several new schemes for calculation of discrete wavelet transforms of images. These schemes reduce the number of steps and, as a consequence, allow to reduce the number of synchronizations on parallel architectures. As an additional useful property, the proposed schemes can reduce also the number of arithmetic operations. The schemes are primarily demonstrated on CDF 5/3 and CDF 9/7 wavelets employed in JPEG 2000 image compression standard. However, the presented method is general, and it can be applied on any wavelet transform. As a result, our scheme requires only two memory barriers for 2-D CDF 5/3 transform compared to four barriers in the original separable form or three barriers in the non-separable scheme recently published. Our reasoning is supported by exhaustive experiments on high-end graphics cards.

Keywords

discrete wavelet transforms, image processing, parallel architectures

Authors

BAŘINA, D.; KULA, M.; ZEMČÍK, P.

Released

1. 10. 2019

ISBN

1861-8200

Periodical

Journal of Real-Time Image Processing

Year of study

16

Number

5

State

Federal Republic of Germany

Pages from

1365

Pages to

1381

Pages count

17

URL

https://www.fit.vut.cz/research/publication/11283/

BibTex

@article{BUT159963,
  author="David {Bařina} and Michal {Kula} and Pavel {Zemčík}",
  title="Parallel Wavelet Schemes for Images",
  journal="Journal of Real-Time Image Processing",
  year="2019",
  volume="16",
  number="5",
  pages="1365--1381",
  doi="10.1007/s11554-016-0646-3",
  issn="1861-8200",
  url="https://www.fit.vut.cz/research/publication/11283/"
}