ICA based algorithms for computing optimal 1-D linear block transforms in variable high-rate source coding

The Karhunen–Loève Transform (KLT) is optimal for transform coding of Gaussian sources, however, it is not optimal, in general, for non-Gaussian sources. Furthermore, under the high-resolution quantization hypothesis, nearly everything is known about the performance of a transform coding system with...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal processing Jg. 88; H. 2; S. 268 - 283
Hauptverfasser: Narozny, Michel, Barret, Michel, Pham, Dinh-Tuan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 01.02.2008
Elsevier Science
Elsevier
Schlagworte:
ISSN:0165-1684, 1872-7557
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The Karhunen–Loève Transform (KLT) is optimal for transform coding of Gaussian sources, however, it is not optimal, in general, for non-Gaussian sources. Furthermore, under the high-resolution quantization hypothesis, nearly everything is known about the performance of a transform coding system with entropy constrained scalar quantization and mean-square distortion. It is then straightforward to find a criterion that, when minimized, gives the optimal linear transform under the abovementioned conditions. However, the optimal transform computation is generally considered as a difficult task and the Gaussian assumption is then used in order to simplify the calculus. In this paper, we present the abovementioned criterion as a contrast of independent component analysis modified by an additional term which is a penalty to non-orthogonality. Then we adapt the icainf algorithm by Pham in order to compute the transform minimizing the criterion either with no constraint or with the orthogonality constraint. Finally, experimental results show that the transforms we introduced can (1) outperform the KLT on synthetic signals, (2) achieve slightly better PSNR for high-rates and better visual quality (preservation of lines and contours) for medium-to-low rates than the KLT and 2-D DCT on grayscale natural images.
AbstractList The Karhunen-Loève Transform (KLT) is optimal for transform coding of Gaussian sources, however, it is not optimal, in general, for non-Gaussian sources. Furthermore, under the high-resolution quantization hypothesis, nearly everything is known about the performance of a transform coding system with entropy constrained scalar quantization and mean-square distortion. It is then straightforward to find a criterion that, when minimized, gives the optimal linear transform under the abovementioned conditions. However, the optimal transform computation is generally considered as a difficult task and the Gaussian assumption is then used in order to simplify the calculus. In this paper, we present the abovementioned criterion as a contrast of independent component analysis modified by an additional term which is a penalty to non-orthogonality. Then we adapt the icainf algorithm by Pham in order to compute the transform minimizing the criterion either with no constraint or with the orthogonality constraint. Finally, experimental results show that the transforms we introduced can (1) outperform the KLT on synthetic signals, (2) achieve slightly better PSNR for high-rates and better visual quality (preservation of lines and contours) for medium-to-low rates than the KLT and 2-D DCT on grayscale natural images.
The Karhunen–Loève Transform (KLT) is optimal for transform coding of Gaussian sources, however, it is not optimal, in general, for non-Gaussian sources. Furthermore, under the high-resolution quantization hypothesis, nearly everything is known about the performance of a transform coding system with entropy constrained scalar quantization and mean-square distortion. It is then straightforward to find a criterion that, when minimized, gives the optimal linear transform under the abovementioned conditions. However, the optimal transform computation is generally considered as a difficult task and the Gaussian assumption is then used in order to simplify the calculus. In this paper, we present the abovementioned criterion as a contrast of independent component analysis modified by an additional term which is a penalty to non-orthogonality. Then we adapt the icainf algorithm by Pham in order to compute the transform minimizing the criterion either with no constraint or with the orthogonality constraint. Finally, experimental results show that the transforms we introduced can (1) outperform the KLT on synthetic signals, (2) achieve slightly better PSNR for high-rates and better visual quality (preservation of lines and contours) for medium-to-low rates than the KLT and 2-D DCT on grayscale natural images.
Author Pham, Dinh-Tuan
Barret, Michel
Narozny, Michel
Author_xml – sequence: 1
  givenname: Michel
  surname: Narozny
  fullname: Narozny, Michel
  email: Michel.Narozny@supelec.fr
  organization: SUPELEC, Information Multimodality & Signal Team, 2 rue É. Belin 57070 Metz, France
– sequence: 2
  givenname: Michel
  surname: Barret
  fullname: Barret, Michel
  email: Michel.Barret@supelec.fr
  organization: SUPELEC, Information Multimodality & Signal Team, 2 rue É. Belin 57070 Metz, France
– sequence: 3
  givenname: Dinh-Tuan
  surname: Pham
  fullname: Pham, Dinh-Tuan
  email: Dinh-Tuan.Pham@imag.fr
  organization: Jean Kuntzmann Laboratory, 51 rue des Mathématiques, BP 53, 38041 Grenoble Cedex 9, France
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=20171839$$DView record in Pascal Francis
https://centralesupelec.hal.science/hal-00278351$$DView record in HAL
BookMark eNqFkUFr3DAQhUVIIZu0_yAHXXLIwRtJ9kp2DoGQtklhoZf2LMbSeFdbrWUkZaH_vjJueuihhQGBeN9j5r1Lcj6GEQm55mzNGZd3h3VyuymGtWBMrefh6oyseKtEpTYbdU5WRbapuGybC3KZ0oExxmvJVuTw5emR9pDQUvC7EF3eHxMdQqQmHKfX7MYdDVN2R_CUVx-pdyNCpL0P5gfNEcZUtIVwIz1BdNB7pHu321cRMtIUXqPBYmWLz3vybgCf8MPv94p8__zp29NLtf36XLbYVqbhMlcSZcOsFR0iWKVqKXoLQ6es7AU02JlO9ULVA7cCauhE24LEusF-wIFx0ddX5Hbx3YPXUyyrx586gNMvj1s9_zEmVFtv-IkX7c2inSAZ8EM5yLj0hxIlSN7WXdHdLzoTQ0oRB21chuzCWDJwXnOm5yb0QS9N6LkJPQ9XBW7-gt_8_4M9LBiWsE4Oo07G4WjQuogmaxvcvw1-ASYxqB0
CODEN SPRODR
CitedBy_id crossref_primary_10_1016_j_sigpro_2008_06_003
crossref_primary_10_1109_TGRS_2010_2083671
crossref_primary_10_1016_j_sigpro_2009_09_011
Cites_doi 10.1109/TCOM.1963.1088759
10.1109/18.850706
10.1109/ICASSP.2007.366087
10.1109/TIT.2004.831787
10.1109/TSP.2006.870641
10.1145/103085.103089
10.1162/089976698300017746
10.1109/29.90373
10.1109/79.952802
10.1016/S0042-6989(97)00121-1
10.1109/LSP.2005.849488
10.1145/214762.214771
10.1109/83.982819
10.1109/TIT.2006.880056
10.1109/TSP.2004.834398
10.1109/78.668554
ContentType Journal Article
Copyright 2007 Elsevier B.V.
2008 INIST-CNRS
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: 2007 Elsevier B.V.
– notice: 2008 INIST-CNRS
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID AAYXX
CITATION
IQODW
1XC
VOOES
DOI 10.1016/j.sigpro.2007.07.017
DatabaseName CrossRef
Pascal-Francis
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle CrossRef
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Applied Sciences
Mathematics
Computer Science
EISSN 1872-7557
EndPage 283
ExternalDocumentID oai:HAL:hal-00278351v1
20171839
10_1016_j_sigpro_2007_07_017
S0165168407002630
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABFNM
ABFRF
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG9
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TAE
TN5
WUQ
XPP
ZMT
~02
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABJNI
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
AFXIZ
AGCQF
AGRNS
BNPGV
IQODW
SSH
1XC
VOOES
ID FETCH-LOGICAL-c416t-6e640dd29eead77362bdaf97d6b2a4e9c97b273f1d2a3a9288a6e34ebfef012b3
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000250889200005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0165-1684
IngestDate Tue Oct 14 20:53:16 EDT 2025
Mon Jul 21 09:11:42 EDT 2025
Tue Nov 18 22:23:29 EST 2025
Sat Nov 29 02:13:24 EST 2025
Fri Feb 23 02:28:11 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Non-Gaussian signals
Image compression
Transform coding
Independent component analysis
Performance evaluation
High resolution
Karhunen Loeve transformation
Source coding
Grey level image
Image processing
Data compression
Entropy
Orthogonality
Algorithm
Varying speed
Image quality
Image coding
Signal quantization
Gaussian signal
Linear transformation
Signal processing
Optimal code
Discrete cosine transforms
Signal to noise ratio
Language English
License https://www.elsevier.com/tdm/userlicense/1.0
CC BY 4.0
Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c416t-6e640dd29eead77362bdaf97d6b2a4e9c97b273f1d2a3a9288a6e34ebfef012b3
ORCID 0000-0001-7133-4444
OpenAccessLink https://centralesupelec.hal.science/hal-00278351
PageCount 16
ParticipantIDs hal_primary_oai_HAL_hal_00278351v1
pascalfrancis_primary_20171839
crossref_citationtrail_10_1016_j_sigpro_2007_07_017
crossref_primary_10_1016_j_sigpro_2007_07_017
elsevier_sciencedirect_doi_10_1016_j_sigpro_2007_07_017
PublicationCentury 2000
PublicationDate 2008-02-01
PublicationDateYYYYMMDD 2008-02-01
PublicationDate_xml – month: 02
  year: 2008
  text: 2008-02-01
  day: 01
PublicationDecade 2000
PublicationPlace Amsterdam
PublicationPlace_xml – name: Amsterdam
PublicationTitle Signal processing
PublicationYear 2008
Publisher Elsevier B.V
Elsevier Science
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier Science
– name: Elsevier
References Witten, Neal, Cleary (bib18) 1987; 30
Gersho, Gray (bib3) 1992
A. T. Puga, A. P. Alves, An experiment on comparing PCA and ICA in classical transform image coding, in: Proceedings of the 1st Workshop on Blind Seperation and ICA, 1998, pp. 105–108.
Amari (bib19) 1998; 10
Cover, Thomas (bib17) 1991
Goyal (bib4) 2001; 18
Pham (bib14) 2004; 52
M. W. Marcellin, M. Gormish, A. Bilgin, M. Boliek, An overview of JPEG2000, in: Proceedings of Data Compression Conference, Snowbird, Utah, March 2000.
Marusic, Deng (bib12) 1999
M. Narozny, M. Barret, ICA-based algorithms applied to image coding, in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Hawaii, USA, April 2007.
Ferreira, Figueiredo (bib13) 2003
Huang, Schultheiss (bib5) September 1963; COM-11
Feng, Effros (bib21) 2002; 11
Wallace (bib1) 1991; 4
Bell, Sejnowski (bib10) 1997; 37
Narozny, Barret, Pham, Akam Bita (bib15) 2005
Goyal, Zhuang, Vetterli (bib2) July 2000; 46
Jana, Moulin (bib8) 2006; 52
Mallat, Falzon (bib7) 1998; 46
Pham (bib20) 2005; 12
Hyvärinen, Tarhunen, Oja (bib23) 2001
Shoham, Gersho (bib24) 1988; 36
Effros, Feng, Zeger (bib6) 2004; 50
Mary, Slock (bib9) 2006; 54
Mary (10.1016/j.sigpro.2007.07.017_bib9) 2006; 54
Witten (10.1016/j.sigpro.2007.07.017_bib18) 1987; 30
Bell (10.1016/j.sigpro.2007.07.017_bib10) 1997; 37
Narozny (10.1016/j.sigpro.2007.07.017_bib15) 2005
Marusic (10.1016/j.sigpro.2007.07.017_bib12) 1999
Goyal (10.1016/j.sigpro.2007.07.017_bib4) 2001; 18
Goyal (10.1016/j.sigpro.2007.07.017_bib2) 2000; 46
Amari (10.1016/j.sigpro.2007.07.017_bib19) 1998; 10
Shoham (10.1016/j.sigpro.2007.07.017_bib24) 1988; 36
Ferreira (10.1016/j.sigpro.2007.07.017_bib13) 2003
Pham (10.1016/j.sigpro.2007.07.017_bib20) 2005; 12
Mallat (10.1016/j.sigpro.2007.07.017_bib7) 1998; 46
Feng (10.1016/j.sigpro.2007.07.017_bib21) 2002; 11
Jana (10.1016/j.sigpro.2007.07.017_bib8) 2006; 52
10.1016/j.sigpro.2007.07.017_bib16
Gersho (10.1016/j.sigpro.2007.07.017_bib3) 1992
Huang (10.1016/j.sigpro.2007.07.017_bib5) 1963; COM-11
10.1016/j.sigpro.2007.07.017_bib11
10.1016/j.sigpro.2007.07.017_bib22
Pham (10.1016/j.sigpro.2007.07.017_bib14) 2004; 52
Cover (10.1016/j.sigpro.2007.07.017_bib17) 1991
Hyvärinen (10.1016/j.sigpro.2007.07.017_bib23) 2001
Wallace (10.1016/j.sigpro.2007.07.017_bib1) 1991; 4
Effros (10.1016/j.sigpro.2007.07.017_bib6) 2004; 50
References_xml – reference: A. T. Puga, A. P. Alves, An experiment on comparing PCA and ICA in classical transform image coding, in: Proceedings of the 1st Workshop on Blind Seperation and ICA, 1998, pp. 105–108.
– start-page: 191
  year: 1999
  end-page: 196
  ident: bib12
  article-title: ICA-FIR based image redundancy reduction
  publication-title: Proceedings of the 1st International Workshop on ICA and Signal Separation
– volume: 52
  start-page: 2690
  year: 2004
  end-page: 2700
  ident: bib14
  article-title: Fast algorithms for mutual information based independent component analysis
  publication-title: IEEE Trans. Signal Process.
– volume: 10
  start-page: 251
  year: 1998
  end-page: 276
  ident: bib19
  article-title: Natural gradient works efficiently in learning
  publication-title: Neural Comput
– volume: 54
  start-page: 1472
  year: 2006
  end-page: 1482
  ident: bib9
  article-title: A theoretical high-rate analysis of causal versus unitary online transform coding
  publication-title: IEEE Trans. Signal Process.
– volume: 46
  start-page: 1027
  year: 1998
  end-page: 1042
  ident: bib7
  article-title: Analysis of low bit rate image transform coding
  publication-title: IEEE Trans. Signal Process.
– reference: M. Narozny, M. Barret, ICA-based algorithms applied to image coding, in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Hawaii, USA, April 2007.
– volume: 46
  start-page: 1623
  year: July 2000
  end-page: 1633
  ident: bib2
  article-title: Transform coding with backward adaptive updates
  publication-title: IEEE Trans. Inform. Theory
– volume: 50
  start-page: 1605
  year: 2004
  end-page: 1619
  ident: bib6
  article-title: Suboptimality of the Karhunen–Loève transform for transform coding
  publication-title: IEEE Trans. Inform. Theory
– volume: 4
  start-page: 30
  year: 1991
  end-page: 40
  ident: bib1
  article-title: Overview of JPEG (ISO/CCITT) still image compression standard
  publication-title: Commun. ACM
– year: 1991
  ident: bib17
  article-title: Elements of Information Theory
– year: 1992
  ident: bib3
  article-title: Vector Quantization and Signal Compression
– volume: 18
  start-page: 9
  year: 2001
  end-page: 21
  ident: bib4
  article-title: Theoretical foundations of transform coding
  publication-title: IEEE Signal Process. Mag.
– volume: 52
  start-page: 4049
  year: 2006
  end-page: 4067
  ident: bib8
  article-title: Optimality of KLT for high-rate transform coding of Gaussian vector-scale mixtures: application to reconstruction, estimation and classification
  publication-title: IEEE Trans. Inform Theory
– start-page: 111
  year: 2005
  end-page: 116
  ident: bib15
  article-title: Modified ICA algorithms for finding optimal transforms in transform coding
  publication-title: Proceedings of the IEEE 4th International Symposium on Image and Signal Processing and Analysis
– year: 2001
  ident: bib23
  article-title: Independent Component Analysis
– volume: 36
  start-page: 1445
  year: 1988
  end-page: 1453
  ident: bib24
  article-title: Efficient bit allocation for an arbitrary set of quantizers
  publication-title: IEEE Trans. Acoustics, Speech Signal Process.
– volume: COM-11
  start-page: 289
  year: September 1963
  end-page: 296
  ident: bib5
  article-title: Block quantization of correlated Gaussian random variables
  publication-title: IEEE Trans. Commun.
– year: 2003
  ident: bib13
  article-title: Class-adapted image compression using independent component analysis
  publication-title: Proceedings of the IEEE International Conference on Image Processing—ICIP’2003
– volume: 37
  start-page: 3327
  year: 1997
  end-page: 3338
  ident: bib10
  article-title: The ‘independent components’ of natural scenes are edge filters
  publication-title: Vision Res.
– volume: 30
  start-page: 519
  year: 1987
  end-page: 540
  ident: bib18
  article-title: Arithmetic coding for data compression
  publication-title: Comm. ACM
– reference: M. W. Marcellin, M. Gormish, A. Bilgin, M. Boliek, An overview of JPEG2000, in: Proceedings of Data Compression Conference, Snowbird, Utah, March 2000.
– volume: 11
  start-page: 113
  year: 2002
  end-page: 122
  ident: bib21
  article-title: On the rate–distortion performance and computational efficiency of the Karhunen–Loève transform for lossy data compression
  publication-title: IEEE Trans. Image Process.
– volume: 12
  start-page: 536
  year: 2005
  end-page: 539
  ident: bib20
  article-title: Entropy of a variable slightly contaminated with another
  publication-title: IEEE Signal Process. Lett.
– volume: COM-11
  start-page: 289
  year: 1963
  ident: 10.1016/j.sigpro.2007.07.017_bib5
  article-title: Block quantization of correlated Gaussian random variables
  publication-title: IEEE Trans. Commun.
  doi: 10.1109/TCOM.1963.1088759
– volume: 46
  start-page: 1623
  year: 2000
  ident: 10.1016/j.sigpro.2007.07.017_bib2
  article-title: Transform coding with backward adaptive updates
  publication-title: IEEE Trans. Inform. Theory
  doi: 10.1109/18.850706
– ident: 10.1016/j.sigpro.2007.07.017_bib16
  doi: 10.1109/ICASSP.2007.366087
– start-page: 111
  year: 2005
  ident: 10.1016/j.sigpro.2007.07.017_bib15
  article-title: Modified ICA algorithms for finding optimal transforms in transform coding
– volume: 50
  start-page: 1605
  issue: 8
  year: 2004
  ident: 10.1016/j.sigpro.2007.07.017_bib6
  article-title: Suboptimality of the Karhunen–Loève transform for transform coding
  publication-title: IEEE Trans. Inform. Theory
  doi: 10.1109/TIT.2004.831787
– year: 1991
  ident: 10.1016/j.sigpro.2007.07.017_bib17
– volume: 54
  start-page: 1472
  issue: 4
  year: 2006
  ident: 10.1016/j.sigpro.2007.07.017_bib9
  article-title: A theoretical high-rate analysis of causal versus unitary online transform coding
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/TSP.2006.870641
– volume: 4
  start-page: 30
  issue: 4
  year: 1991
  ident: 10.1016/j.sigpro.2007.07.017_bib1
  article-title: Overview of JPEG (ISO/CCITT) still image compression standard
  publication-title: Commun. ACM
  doi: 10.1145/103085.103089
– volume: 10
  start-page: 251
  issue: 2
  year: 1998
  ident: 10.1016/j.sigpro.2007.07.017_bib19
  article-title: Natural gradient works efficiently in learning
  publication-title: Neural Comput
  doi: 10.1162/089976698300017746
– volume: 36
  start-page: 1445
  issue: 9
  year: 1988
  ident: 10.1016/j.sigpro.2007.07.017_bib24
  article-title: Efficient bit allocation for an arbitrary set of quantizers
  publication-title: IEEE Trans. Acoustics, Speech Signal Process.
  doi: 10.1109/29.90373
– ident: 10.1016/j.sigpro.2007.07.017_bib11
– volume: 18
  start-page: 9
  issue: 5
  year: 2001
  ident: 10.1016/j.sigpro.2007.07.017_bib4
  article-title: Theoretical foundations of transform coding
  publication-title: IEEE Signal Process. Mag.
  doi: 10.1109/79.952802
– volume: 37
  start-page: 3327
  year: 1997
  ident: 10.1016/j.sigpro.2007.07.017_bib10
  article-title: The ‘independent components’ of natural scenes are edge filters
  publication-title: Vision Res.
  doi: 10.1016/S0042-6989(97)00121-1
– volume: 12
  start-page: 536
  issue: 7
  year: 2005
  ident: 10.1016/j.sigpro.2007.07.017_bib20
  article-title: Entropy of a variable slightly contaminated with another
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2005.849488
– year: 1992
  ident: 10.1016/j.sigpro.2007.07.017_bib3
– volume: 30
  start-page: 519
  issue: 6
  year: 1987
  ident: 10.1016/j.sigpro.2007.07.017_bib18
  article-title: Arithmetic coding for data compression
  publication-title: Comm. ACM
  doi: 10.1145/214762.214771
– volume: 11
  start-page: 113
  issue: 2
  year: 2002
  ident: 10.1016/j.sigpro.2007.07.017_bib21
  article-title: On the rate–distortion performance and computational efficiency of the Karhunen–Loève transform for lossy data compression
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/83.982819
– start-page: 191
  year: 1999
  ident: 10.1016/j.sigpro.2007.07.017_bib12
  article-title: ICA-FIR based image redundancy reduction
– volume: 52
  start-page: 4049
  issue: 9
  year: 2006
  ident: 10.1016/j.sigpro.2007.07.017_bib8
  article-title: Optimality of KLT for high-rate transform coding of Gaussian vector-scale mixtures: application to reconstruction, estimation and classification
  publication-title: IEEE Trans. Inform Theory
  doi: 10.1109/TIT.2006.880056
– volume: 52
  start-page: 2690
  issue: 10
  year: 2004
  ident: 10.1016/j.sigpro.2007.07.017_bib14
  article-title: Fast algorithms for mutual information based independent component analysis
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/TSP.2004.834398
– year: 2003
  ident: 10.1016/j.sigpro.2007.07.017_bib13
  article-title: Class-adapted image compression using independent component analysis
– ident: 10.1016/j.sigpro.2007.07.017_bib22
– volume: 46
  start-page: 1027
  issue: 4
  year: 1998
  ident: 10.1016/j.sigpro.2007.07.017_bib7
  article-title: Analysis of low bit rate image transform coding
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/78.668554
– year: 2001
  ident: 10.1016/j.sigpro.2007.07.017_bib23
SSID ssj0001360
Score 1.9151654
Snippet The Karhunen–Loève Transform (KLT) is optimal for transform coding of Gaussian sources, however, it is not optimal, in general, for non-Gaussian sources....
The Karhunen-Loève Transform (KLT) is optimal for transform coding of Gaussian sources, however, it is not optimal, in general, for non-Gaussian sources....
SourceID hal
pascalfrancis
crossref
elsevier
SourceType Open Access Repository
Index Database
Enrichment Source
Publisher
StartPage 268
SubjectTerms Applied sciences
Coding, codes
Computer Science
Detection, estimation, filtering, equalization, prediction
Engineering Sciences
Exact sciences and technology
Image compression
Independent component analysis
Information, signal and communications theory
Mathematics
Miscellaneous
Non-Gaussian signals
Optimization and Control
Sampling, quantization
Signal and communications theory
Signal and Image Processing
Signal processing
Signal, noise
Telecommunications and information theory
Transform coding
Title ICA based algorithms for computing optimal 1-D linear block transforms in variable high-rate source coding
URI https://dx.doi.org/10.1016/j.sigpro.2007.07.017
https://centralesupelec.hal.science/hal-00278351
Volume 88
WOSCitedRecordID wos000250889200005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-7557
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001360
  issn: 0165-1684
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bj9JAFJ4g64PGeFk14mUzMb6R2dBp6bSPuOwGFAnJouGtmbZTLmIh3LL6r_yHnulcKCFm1weTZgLTzkA5X8-Nc0HogxP7cUabARFhwyWeTwXhIs4IA2aZunHixEUfsm891u8Ho1E4qFR-m1yY3ZzleXBzEy7_K6lhDogtU2f_gdx2U5iA10B0GIHsMN6J8N2LVl3KprTO5-MF2P4TVXOhiB7fqihn4BM_gDYOadelmslXMoA9-S4bRig1toiS3YEdXWRWyZrGRNaUqCtfP2xlRZ5WbK-nY6nXLlXegTkpvcx8tfiV_zQh-sJGdHwsgoSP5wc6c7s9zSdkuNXoNY6JwMQyG2-ZFu1l56XfJI6vWsKdC8VwAwYaflMVqTYcOQhKyKNl9qpa8GhJTVULnCMhoPwRs_P1dAx3rctUwqGSRA9rbnda19GgfRX1uv3Ph2dLgYqdVg_GCZ-T4o9at-nswOA-oawZBlV00upejj5Z8e-4RWq6vVmTr1kEFR5_pb_pQ_cmMjD30ZKv4VnNVJOVkuYzfIoea5MFtxTUnqGKyE_RE9MOBGvpcIoelmpbwrsvtiDw-jmaASpxgUq8RyUGpGGLSqxRiQGVWKESF6jEe1TiaY4NKrFFJVaoxAqVL9DXq8vhRYfoNh8kAWtgQ3zhe400paEArsYkk4hTnoUs9WPKPREmIYtByc6clHKXhzQIuC9cDziKyEC9it2XqJovcvEK4ZiCBOMUVooMVjpBRkUKy0UjzFzPa9SQa37sKNE18GUrlnlkgh1nkSKRbM_KInk4rIaIXbVUNWBuuZ4ZOkZaj1X6aQQIvWXleyC7_RBZ-h2wF8m5PfJq6OwAFfZyKmtfgcHz-i67vEEP9g_tW1TdrLbiHbqf7DbT9epMg_oPcLjWwg
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=ICA+based+algorithms+for+computing+optimal+1-D+linear+block+transforms+in+variable+high-rate+source+coding&rft.jtitle=Signal+processing&rft.au=Narozny%2C+Michel&rft.au=Barret%2C+Michel&rft.au=Pham%2C+Dinh-Tuan&rft.date=2008-02-01&rft.pub=Elsevier&rft.issn=0165-1684&rft.eissn=1872-7557&rft.volume=88&rft.issue=2&rft.spage=268&rft.epage=283&rft_id=info:doi/10.1016%2Fj.sigpro.2007.07.017&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-00278351v1
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0165-1684&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0165-1684&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0165-1684&client=summon