Title: Storage space reduction in picture archiving and communication system using generative adversarial network

Authors: Bejoy Varghese; S. Krishnakumar

Addresses: Federal Institute of Science And Technology, HormisNagar, Angamaly, Kerala, India ' M.G University, Kottayam, Kerala, India

Abstract: This paper presents a new architecture of picture archiving and communication system (PACS) based on generative adversarial network (GAN) and fractal image compression (FIC). The GAN architecture is modified to be a conditional GAN by conditioning the generator with the uncompressed image. Both the generator and discriminator networks utilise the convolutional neural network (CNN) which enables the system to capture the similarity measures without using any handcrafted functions. Performance of the proposed design is evaluated by comparing it with the commonly used compression techniques in PACS and recently reported best performing machine learning compression techniques. The simulation of PACS shows that the storage space consumption of the proposed design is only 30% in comparison with other algorithms. It is also observed that the GAN-based FIC can drastically reduce the compression time compared to the conventional fractal and non fractal compression methods.

Keywords: image compression; picture archiving and communication system; PACS; generative adversarial network; GAN; fractal compression.

DOI: 10.1504/IJAHUC.2023.130981

International Journal of Ad Hoc and Ubiquitous Computing, 2023 Vol.43 No.1, pp.41 - 52

Received: 07 Sep 2021
Received in revised form: 24 Aug 2022
Accepted: 05 Sep 2022

Published online: 17 May 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article