Enhancement of images compression using channel attention and post-filtering based on deep autoencoder

Image compression is a crucial research topic in today's information age, especially to meet the demand for balanced data compression efficiency with the quality of the resulting image reconstruction. Common methods used for image compression nowadays are based on autoencoders with deep learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Andri Agustav Wirabudi, Nurwan Reza Fachrurrozi, Pietra Dorand, Muhamad Royhan
Format: Article
Language:English
Published: Universitas Ahmad Dahlan 2024-08-01
Series:IJAIN (International Journal of Advances in Intelligent Informatics)
Subjects:
Online Access:https://ijain.org/index.php/IJAIN/article/view/1499
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846099793970987008
author Andri Agustav Wirabudi
Nurwan Reza Fachrurrozi
Pietra Dorand
Muhamad Royhan
author_facet Andri Agustav Wirabudi
Nurwan Reza Fachrurrozi
Pietra Dorand
Muhamad Royhan
author_sort Andri Agustav Wirabudi
collection DOAJ
description Image compression is a crucial research topic in today's information age, especially to meet the demand for balanced data compression efficiency with the quality of the resulting image reconstruction. Common methods used for image compression nowadays are based on autoencoders with deep learning foundations. However, these methods have limitations as they only consider residual values in processed images to achieve existing compression efficiency with less satisfying reconstruction results. To address this issue, we introduce the Attention Block mechanism to improve coding efficiency even further. Additionally, we introduce post-filtering methods to enhance the final reconstruction results of images. Experimental results using two datasets, CLIC for training and KODAK for testing, demonstrate that this method outperforms several previous research methods. With an efficiency coding improvement of -28.16%, an average PSNR improvement of 34%, and an MS-SSIM improvement of 8%, the model in this study significantly enhances the rate-distortion (RD) performance compared to previous approaches.
format Article
id doaj-art-4b75c9401af74a9dbc348da36c5700d6
institution Kabale University
issn 2442-6571
2548-3161
language English
publishDate 2024-08-01
publisher Universitas Ahmad Dahlan
record_format Article
series IJAIN (International Journal of Advances in Intelligent Informatics)
spelling doaj-art-4b75c9401af74a9dbc348da36c5700d62024-12-31T05:50:57ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612024-08-0110342544010.26555/ijain.v10i3.1499306Enhancement of images compression using channel attention and post-filtering based on deep autoencoderAndri Agustav Wirabudi0Nurwan Reza Fachrurrozi1Pietra Dorand2Muhamad Royhan3Department of Intelligence Media Engineering, Hanbat National University School of Applied ScienceSchool of Applied Science, Telkom UniversitySchool of Applied Science, Telkom UniversitySchool of Applied Science, Telkom UniversityImage compression is a crucial research topic in today's information age, especially to meet the demand for balanced data compression efficiency with the quality of the resulting image reconstruction. Common methods used for image compression nowadays are based on autoencoders with deep learning foundations. However, these methods have limitations as they only consider residual values in processed images to achieve existing compression efficiency with less satisfying reconstruction results. To address this issue, we introduce the Attention Block mechanism to improve coding efficiency even further. Additionally, we introduce post-filtering methods to enhance the final reconstruction results of images. Experimental results using two datasets, CLIC for training and KODAK for testing, demonstrate that this method outperforms several previous research methods. With an efficiency coding improvement of -28.16%, an average PSNR improvement of 34%, and an MS-SSIM improvement of 8%, the model in this study significantly enhances the rate-distortion (RD) performance compared to previous approaches.https://ijain.org/index.php/IJAIN/article/view/1499channel attentionauto encoderpost-filteringdeep learningautoendcoder
spellingShingle Andri Agustav Wirabudi
Nurwan Reza Fachrurrozi
Pietra Dorand
Muhamad Royhan
Enhancement of images compression using channel attention and post-filtering based on deep autoencoder
IJAIN (International Journal of Advances in Intelligent Informatics)
channel attention
auto encoder
post-filtering
deep learning
autoendcoder
title Enhancement of images compression using channel attention and post-filtering based on deep autoencoder
title_full Enhancement of images compression using channel attention and post-filtering based on deep autoencoder
title_fullStr Enhancement of images compression using channel attention and post-filtering based on deep autoencoder
title_full_unstemmed Enhancement of images compression using channel attention and post-filtering based on deep autoencoder
title_short Enhancement of images compression using channel attention and post-filtering based on deep autoencoder
title_sort enhancement of images compression using channel attention and post filtering based on deep autoencoder
topic channel attention
auto encoder
post-filtering
deep learning
autoendcoder
url https://ijain.org/index.php/IJAIN/article/view/1499
work_keys_str_mv AT andriagustavwirabudi enhancementofimagescompressionusingchannelattentionandpostfilteringbasedondeepautoencoder
AT nurwanrezafachrurrozi enhancementofimagescompressionusingchannelattentionandpostfilteringbasedondeepautoencoder
AT pietradorand enhancementofimagescompressionusingchannelattentionandpostfilteringbasedondeepautoencoder
AT muhamadroyhan enhancementofimagescompressionusingchannelattentionandpostfilteringbasedondeepautoencoder