A. R. Calderbank, I. Daubechies, W. Sweldens, and B.-L. Yeo :
“Lossless image compression using integer to integer wavelet transforms 596–599
in
1st international conference on image processing
(Santa Barbara, CA, 26–29 October 1997 ),
vol. 1 .
IEEE (Piscataway, NJ ),
1997 .
incollection
Abstract
People
BibTeX
@incollection {key71393781,
AUTHOR = {Calderbank, A. R. and Daubechies, I.
and Sweldens, W. and Yeo, B.-L.},
TITLE = {Lossless image compression using integer
to integer wavelet transforms},
BOOKTITLE = {1st international conference on image
processing},
VOLUME = {1},
PUBLISHER = {IEEE},
ADDRESS = {Piscataway, NJ},
YEAR = {1997},
PAGES = {596--599},
DOI = {10.1109/ICIP.1997.647983},
NOTE = {(Santa Barbara, CA, 26--29 October 1997).},
ISBN = {9780818681837},
}
A. R. Calderbank, I. Daubechies, W. Sweldens, and B.-L. Yeo :
“Wavelet transforms that map integers to integers Appl. Comput. Harmon. Anal.
5 : 3
(July 1998 ),
pp. 332–369 .
MR
1632537 Zbl
0941.42017 article
Abstract
People
BibTeX
Invertible wavelet transforms that map integers to integers have important applications in lossless coding. In this paper we present two approaches to build integer to integer wavelet transforms. The first approach is to adapt the precoder of Laroia et al. , which is used in information transmission; we combine it with expansion factors for the high and low pass band in subband filtering. The second approach builds upon the idea of factoring wavelet transforms into so-called lifting steps. This allows the construction of an integer version of every wavelet transform. Finally, we use these approaches in a lossless image coder and compare the results to those given in the literature.
@article {key1632537m,
AUTHOR = {Calderbank, A. R. and Daubechies, Ingrid
and Sweldens, Wim and Yeo, Boon-Lock},
TITLE = {Wavelet transforms that map integers
to integers},
JOURNAL = {Appl. Comput. Harmon. Anal.},
FJOURNAL = {Applied and Computational Harmonic Analysis},
VOLUME = {5},
NUMBER = {3},
MONTH = {July},
YEAR = {1998},
PAGES = {332--369},
DOI = {10.1006/acha.1997.0238},
NOTE = {MR:1632537. Zbl:0941.42017.},
ISSN = {1063-5203},
}
A. R. Calderbank and I. Daubechies :
“The pros and cons of democracy 1721–1725
in
Shannon theory: Perspective, trends, and applications: Special issue dedicated to Aaron D. Wyner ,
published as IEEE Trans. Inform. Theory
48 : 6 .
Issue edited by H. J. Landau, J. E. Mazo, S. Shamai, and J. Ziv .
IEEE (New York ),
June 2002 .
MR
1902984 Zbl
1061.94014 incollection
Abstract
People
BibTeX
We introduce the concept of “democracy,” in which the individual bits in a coarsely quantized representation of a signal are all given “equal weight” in the approximation to the original signal. We prove that such democratic representations cannot achieve the same accuracy as optimal nondemocratic schemes.
@article {key1902984m,
AUTHOR = {Calderbank, A. R. and Daubechies, I.},
TITLE = {The pros and cons of democracy},
JOURNAL = {IEEE Trans. Inform. Theory},
FJOURNAL = {Institute of Electrical and Electronics
Engineers. Transactions on Information
Theory},
VOLUME = {48},
NUMBER = {6},
MONTH = {June},
YEAR = {2002},
PAGES = {1721--1725},
DOI = {10.1109/TIT.2002.1003852},
NOTE = {\textit{Shannon theory: {P}erspective,
trends, and applications: {S}pecial
issue dedicated to {A}aron {D}. {W}yner}.
Issue edited by H. J. Landau,
J. E. Mazo, S. Shamai,
and J. Ziv. MR:1902984. Zbl:1061.94014.},
ISSN = {0018-9448},
}
J. Wolff, M. Martens, S. Jafarpour, I. Daubechies, and R. Calderbank :
“Uncovering elements of style 1017–1020
in
2011 IEEE international conference on acoustics, speech and signal processing
(Prague, 22–27 May 2011 ).
IEEE (Piscataway, NJ ),
2011 .
incollection
Abstract
People
BibTeX
This paper relates the style of 16th century Flemish paintings by Goossen van der Weyden to the style of preliminary sketches or underpaintings made prior to executing the painting. Van der Weyden made underpaintings in markedly different styles for reasons as yet not understood by art historians. The analysis presented here starts from a classification of the underpaintings into four distinct styles by experts in art history. Analysis of the painted surfaces by a combination of wavelet analysis, hidden Markov trees and boosting algorithms can distinguish the four underpainting styles with greater than \( 90\% \) cross-validation accuracy. On a subsequent blind test this classifier provided insight into the hypothesis by art historians that different patches of the finished painting were executed by different hands.
@incollection {key29907936,
AUTHOR = {Wolff, Josephine and Martens, Maximiliaan
and Jafarpour, Sina and Daubechies,
Ingrid and Calderbank, Robert},
TITLE = {Uncovering elements of style},
BOOKTITLE = {2011 {IEEE} international conference
on acoustics, speech and signal processing},
PUBLISHER = {IEEE},
ADDRESS = {Piscataway, NJ},
YEAR = {2011},
PAGES = {1017--1020},
DOI = {10.1109/ICASSP.2011.5946579},
NOTE = {(Prague, 22--27 May 2011).},
ISBN = {9781457705397},
}
T. Wu, G. Polatkan, D. Steel, W. Brown, I. Daubechies, and R. Calderbank :
“Painting analysis using wavelets and probabilistic topic models 3264–3268
in
2013 IEEE international conference on image processing
(Melbourne, 15–18 September 2013 ).
IEEE (Piscataway, NJ ),
2013 .
ArXiv
1401.6638 incollection
Abstract
People
BibTeX
In this paper, computer-based techniques for stylistic analysis of paintings are applied to the five panels of the 14th century Peruzzi Altarpiece by Giotto di Bondone. Features are extracted by combining a dual-tree complex wavelet transform with a hidden Markov tree (HMT) model. Hierarchical clustering is used to identify stylistic keywords in image patches, and keyword frequencies are calculated for sub-images that each contains many patches. A generative hierarchical Bayesian model learns stylistic patterns of keywords; these patterns are then used to characterize the styles of the sub-images; this in turn, permits to discriminate between paintings. Results suggest that such unsupervised probabilistic topic models can be useful to distill characteristic elements of style.
@incollection {key1401.6638a,
AUTHOR = {Wu, Tong and Polatkan, G\"ung\"or and
Steel, David and Brown, William and
Daubechies, Ingrid and Calderbank, Robert},
TITLE = {Painting analysis using wavelets and
probabilistic topic models},
BOOKTITLE = {2013 {IEEE} international conference
on image processing},
PUBLISHER = {IEEE},
ADDRESS = {Piscataway, NJ},
YEAR = {2013},
PAGES = {3264--3268},
DOI = {10.1109/ICIP.2013.6738672},
NOTE = {(Melbourne, 15--18 September 2013).
ArXiv:1401.6638.},
ISBN = {9781479923410},
}
W. Zhu, Q. Qiu, J. Huang, R. Calderbank, G. Sapiro, and I. Daubechies :
“LDMNet: Low dimensional manifold regularized neural networks 2743–2751
in
2018 IEEE/CVF conference on computer vision and pattern recognition
(Salt Lake City, UT, 18–23 June 2018 ).
IEEE (Piscataway, NJ ),
2018 .
ArXiv
1711.06246 incollection
Abstract
People
BibTeX
Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers from overfitting. Many existing methods of reducing overfitting are data-independent. Data-dependent regularizations are mostly motivated by the observation that data of interest lie close to a manifold, which is typically hard to parametrize explicitly. These methods usually only focus on the geometry of the input data, and do not necessarily encourage the networks to produce geometrically meaningful features. To resolve this, we propose the Low-Dimensional-Manifold-regularized neural Network (LDMNet), which incorporates a feature regularization method that focuses on the geometry of both the input data and the output features. In LDMNet, we regularize the network by encouraging the combination of the input data and the output features to sample a collection of low dimensional manifolds, which are searched efficiently without explicit parametrization. To achieve this, we directly use the manifold dimension as a regularization term in a variational functional. The resulting Euler–Lagrange equation is a Laplace–Beltrami equation over a point cloud, which is solved by the point integral method without increasing the computational complexity. In the experiments, we show that LDMNet significantly outperforms widely-used regularizers. Moreover, LDMNet can extract common features of an object imaged via different modalities, which is very useful in real-world applications such as cross-spectral face recognition.
@incollection {key1711.06246a,
AUTHOR = {Zhu, Wei and Qiu, Qiang and Huang, Jiaji
and Calderbank, Robert and Sapiro, Guillermo
and Daubechies, Ingrid},
TITLE = {L{DMN}et: {L}ow dimensional manifold
regularized neural networks},
BOOKTITLE = {2018 {IEEE}/{CVF} conference on computer
vision and pattern recognition},
PUBLISHER = {IEEE},
ADDRESS = {Piscataway, NJ},
YEAR = {2018},
PAGES = {2743--2751},
DOI = {10.1109/CVPR.2018.00290},
NOTE = {(Salt Lake City, UT, 18--23 June 2018).
ArXiv:1711.06246.},
ISSN = {2575-7075},
ISBN = {9781538664209},
}
