Region of interest scalable image compression using semantic communications

Samarathunga, Prabhath and Gowrisetty, Vishnu and Fernando, Thanuj and Ganearachchi, Yasith and Fernando, Anil; (2023) Region of interest scalable image compression using semantic communications. In: IEEE 42nd International Conference on Consumer Electronics. IEEE, USA. (In Press)

[thumbnail of Samarathunga-etal-IEEE-2024-Region-of-interest-scalable-image-compression-using-semantic-communications]
Preview
 Text. Filename: Samarathunga-etal-IEEE-2024-Region-of-interest-scalable-image-compression-using-semantic-communications.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (8MB)| Preview

Abstract

Growing consumer demand for media content over a wide range of devices has made scalable image compression vital in today’s media landscape. Image compression is conventionally achieved by means of statistical signal processing, but since recently, deep learning techniques are seen to be widely as well. Capabilities of such systems also enable accurate identification of regions of interest in images, leading optimised performance in most applications. This paper proposes a region-of-interest scalable image compression system using semantic communications, where an autoencoder-based semantic encoder performs the base level compression, while a Semantic Mask Extracting Transformer (SeMExT) enables identification of regions of interest to create enhancement layers with different quality levels using a scalable JPEG encoder. When benchmarked against scalable JPEG across a variety of images, the proposed system demonstrates significantly improved compressive performance. The base layer achieved 61.4 times more compression on average, along with better rate-distortion performance at any given quality level.

ORCID iDs

Samarathunga, Prabhath, Gowrisetty, Vishnu, Fernando, Thanuj, Ganearachchi, Yasith ORCID logoORCID: https://orcid.org/0000-0002-8337-3739 and Fernando, Anil;
  • Item type:Book Section
    ID code:88129
    Dates:
    Date
    Event
    1 November 2023
    Published
    1 November 2023
    Accepted
    Notes:© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Subjects:Science > Mathematics > Electronic computers. Computer science
    Department:Faculty of Science > Computer and Information Sciences
    Depositing user: Pure Administrator
    Date deposited:08 Feb 2024 11:56
    Last modified:11 Nov 2024 15:34
    URI:https://strathprints.strath.ac.uk/id/eprint/88129
CORE (COnnecting REpositories)