A Machine Learning Approach to Optimal Inverse Discrete Cosine Transform (IDCT) Design

The design of the optimal inverse discrete cosine transform (IDCT) to compensate the quantization error is proposed for effective lossy image compression in this work. The forward and inverse DCTs are designed in pair in current image/video coding standards without taking the quantization effect int...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	arXiv.org 2021-01
Hauptverfasser:	Wang, Yifan, Zhanxuan Mei, Chia-Yang, Tsai, Katsavounidis, Ioannis, C -C Jay Kuo
Format:	Artikel
Sprache:	eng
Schlagworte:	Coding standards Discrete cosine transform Error compensation Image coding Image compression Image quality JPEG encoders-decoders Machine learning Measurement Q factors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title	arXiv.org
container_volume
creator	Wang, Yifan Zhanxuan Mei Chia-Yang, Tsai Katsavounidis, Ioannis C -C Jay Kuo
description	The design of the optimal inverse discrete cosine transform (IDCT) to compensate the quantization error is proposed for effective lossy image compression in this work. The forward and inverse DCTs are designed in pair in current image/video coding standards without taking the quantization effect into account. Yet, the distribution of quantized DCT coefficients deviate from that of original DCT coefficients. This is particularly obvious when the quality factor of JPEG compressed images is small. To address this problem, we first use a set of training images to learn the compound effect of forward DCT, quantization and dequantization in cascade. Then, a new IDCT kernel is learned to reverse the effect of such a pipeline. Experiments are conducted to demonstrate that the advantage of the new method, which has a gain of 0.11-0.30dB over the standard JPEG over a wide range of quality factors.
format	Article
fullrecord	<record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2485339702</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2485339702</sourcerecordid><originalsourceid>FETCH-proquest_journals_24853397023</originalsourceid><addsrcrecordid>eNqNjMEKgkAURYcgSMp_eNCmFoLNaNpStCgo2khbGeRpIzpj87Tvz6APaHXhnnvujDlciJ0XB5wvmEvU-L7P9xEPQ-GwRwI3WT6VRriitFrpGpK-t2YqYTBw7wfVyRYu-o2WEDJFpcUBITX0lXIrNVXGdrC5ZGm-hQxJ1XrF5pVsCd1fLtn6dMzTszc9v0akoWjMaPWECh7EoRCHyOfiv9UHPjM_mQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2485339702</pqid></control><display><type>article</type><title>A Machine Learning Approach to Optimal Inverse Discrete Cosine Transform (IDCT) Design</title><source>Free E- Journals</source><creator>Wang, Yifan ; Zhanxuan Mei ; Chia-Yang, Tsai ; Katsavounidis, Ioannis ; C -C Jay Kuo</creator><creatorcontrib>Wang, Yifan ; Zhanxuan Mei ; Chia-Yang, Tsai ; Katsavounidis, Ioannis ; C -C Jay Kuo</creatorcontrib><description>The design of the optimal inverse discrete cosine transform (IDCT) to compensate the quantization error is proposed for effective lossy image compression in this work. The forward and inverse DCTs are designed in pair in current image/video coding standards without taking the quantization effect into account. Yet, the distribution of quantized DCT coefficients deviate from that of original DCT coefficients. This is particularly obvious when the quality factor of JPEG compressed images is small. To address this problem, we first use a set of training images to learn the compound effect of forward DCT, quantization and dequantization in cascade. Then, a new IDCT kernel is learned to reverse the effect of such a pipeline. Experiments are conducted to demonstrate that the advantage of the new method, which has a gain of 0.11-0.30dB over the standard JPEG over a wide range of quality factors.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Coding standards ; Discrete cosine transform ; Error compensation ; Image coding ; Image compression ; Image quality ; JPEG encoders-decoders ; Machine learning ; Measurement ; Q factors</subject><ispartof>arXiv.org, 2021-01</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Wang, Yifan</creatorcontrib><creatorcontrib>Zhanxuan Mei</creatorcontrib><creatorcontrib>Chia-Yang, Tsai</creatorcontrib><creatorcontrib>Katsavounidis, Ioannis</creatorcontrib><creatorcontrib>C -C Jay Kuo</creatorcontrib><title>A Machine Learning Approach to Optimal Inverse Discrete Cosine Transform (IDCT) Design</title><title>arXiv.org</title><description>The design of the optimal inverse discrete cosine transform (IDCT) to compensate the quantization error is proposed for effective lossy image compression in this work. The forward and inverse DCTs are designed in pair in current image/video coding standards without taking the quantization effect into account. Yet, the distribution of quantized DCT coefficients deviate from that of original DCT coefficients. This is particularly obvious when the quality factor of JPEG compressed images is small. To address this problem, we first use a set of training images to learn the compound effect of forward DCT, quantization and dequantization in cascade. Then, a new IDCT kernel is learned to reverse the effect of such a pipeline. Experiments are conducted to demonstrate that the advantage of the new method, which has a gain of 0.11-0.30dB over the standard JPEG over a wide range of quality factors.</description><subject>Coding standards</subject><subject>Discrete cosine transform</subject><subject>Error compensation</subject><subject>Image coding</subject><subject>Image compression</subject><subject>Image quality</subject><subject>JPEG encoders-decoders</subject><subject>Machine learning</subject><subject>Measurement</subject><subject>Q factors</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjMEKgkAURYcgSMp_eNCmFoLNaNpStCgo2khbGeRpIzpj87Tvz6APaHXhnnvujDlciJ0XB5wvmEvU-L7P9xEPQ-GwRwI3WT6VRriitFrpGpK-t2YqYTBw7wfVyRYu-o2WEDJFpcUBITX0lXIrNVXGdrC5ZGm-hQxJ1XrF5pVsCd1fLtn6dMzTszc9v0akoWjMaPWECh7EoRCHyOfiv9UHPjM_mQ</recordid><startdate>20210131</startdate><enddate>20210131</enddate><creator>Wang, Yifan</creator><creator>Zhanxuan Mei</creator><creator>Chia-Yang, Tsai</creator><creator>Katsavounidis, Ioannis</creator><creator>C -C Jay Kuo</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210131</creationdate><title>A Machine Learning Approach to Optimal Inverse Discrete Cosine Transform (IDCT) Design</title><author>Wang, Yifan ; Zhanxuan Mei ; Chia-Yang, Tsai ; Katsavounidis, Ioannis ; C -C Jay Kuo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24853397023</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Coding standards</topic><topic>Discrete cosine transform</topic><topic>Error compensation</topic><topic>Image coding</topic><topic>Image compression</topic><topic>Image quality</topic><topic>JPEG encoders-decoders</topic><topic>Machine learning</topic><topic>Measurement</topic><topic>Q factors</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Yifan</creatorcontrib><creatorcontrib>Zhanxuan Mei</creatorcontrib><creatorcontrib>Chia-Yang, Tsai</creatorcontrib><creatorcontrib>Katsavounidis, Ioannis</creatorcontrib><creatorcontrib>C -C Jay Kuo</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Yifan</au><au>Zhanxuan Mei</au><au>Chia-Yang, Tsai</au><au>Katsavounidis, Ioannis</au><au>C -C Jay Kuo</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Machine Learning Approach to Optimal Inverse Discrete Cosine Transform (IDCT) Design</atitle><jtitle>arXiv.org</jtitle><date>2021-01-31</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>The design of the optimal inverse discrete cosine transform (IDCT) to compensate the quantization error is proposed for effective lossy image compression in this work. The forward and inverse DCTs are designed in pair in current image/video coding standards without taking the quantization effect into account. Yet, the distribution of quantized DCT coefficients deviate from that of original DCT coefficients. This is particularly obvious when the quality factor of JPEG compressed images is small. To address this problem, we first use a set of training images to learn the compound effect of forward DCT, quantization and dequantization in cascade. Then, a new IDCT kernel is learned to reverse the effect of such a pipeline. Experiments are conducted to demonstrate that the advantage of the new method, which has a gain of 0.11-0.30dB over the standard JPEG over a wide range of quality factors.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext	fulltext
identifier	EISSN: 2331-8422
ispartof	arXiv.org, 2021-01
issn	2331-8422
language	eng
recordid	cdi_proquest_journals_2485339702
source	Free E- Journals
subjects	Coding standards Discrete cosine transform Error compensation Image coding Image compression Image quality JPEG encoders-decoders Machine learning Measurement Q factors
title	A Machine Learning Approach to Optimal Inverse Discrete Cosine Transform (IDCT) Design
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T12%3A49%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20Machine%20Learning%20Approach%20to%20Optimal%20Inverse%20Discrete%20Cosine%20Transform%20(IDCT)%20Design&rft.jtitle=arXiv.org&rft.au=Wang,%20Yifan&rft.date=2021-01-31&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2485339702%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2485339702&rft_id=info:pmid/&rfr_iscdi=true