Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Bertrand Augereau"'
Publikováno v:
Journal of Electrical and Electronics Engineering, Vol 1, Iss 1, Pp 198-201 (2008)
This paper consist in a comparative studybetween some differential motion estimation methodsthat could be applied in the case of medical diagnosisby using motion information in image sequences.The studied algorithms could be applied in the caseof the
Externí odkaz:
https://doaj.org/article/a83fbf25321445589b500dcd34c42ebc
Autor:
Bertrand Augereau, Philippe Carr
Publikováno v:
Signal Processing
Signal Processing, Elsevier, 2016, Available online 7 December 2016, ⟨10.1016/j.sigpro.2016.11.022⟩
Signal Processing, Elsevier, 2016, Available online 7 December 2016, ⟨10.1016/j.sigpro.2016.11.022⟩
Starting from a link with the discrete polynomial decomposition, we propose an extension of the non-uniform filter bank framework to vector-valued signals to carry out a non marginal color wavelet transform. Recently quaternions or Clifford algebras
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6e0aa22617e706041ebcfa3083e2bec
https://hal.archives-ouvertes.fr/hal-01468089
https://hal.archives-ouvertes.fr/hal-01468089
Publikováno v:
Journal of Electronic Imaging
Journal of Electronic Imaging, SPIE and IS&T, 2015, 24 (6), ⟨10.1117/1.JEI.24.6.061114⟩
Journal of Electronic Imaging, SPIE and IS&T, 2015, Special Section on Quality Control by Artificial Vision: Nonconventional Imaging Systems, 24 (Issue 6), ⟨10.1117/1.JEI.24.6.061114⟩
Journal of Electronic Imaging, SPIE and IS&T, 2015, 24 (6), ⟨10.1117/1.JEI.24.6.061114⟩
Journal of Electronic Imaging, SPIE and IS&T, 2015, Special Section on Quality Control by Artificial Vision: Nonconventional Imaging Systems, 24 (Issue 6), ⟨10.1117/1.JEI.24.6.061114⟩
International audience; This paper addresses the use of orthogonal Polynomial Basis transform in video classification due to its multiple advantages, especially for multiscale and multiresolution analysis similar to the wavelet transform. In our appr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02a84a02e43f114e4d6448640591d522
https://hal.archives-ouvertes.fr/hal-01228089/document
https://hal.archives-ouvertes.fr/hal-01228089/document
Publikováno v:
QCAV
QCAV, Jun 2015, Le Creusot, France
Twelfth International Conference on Quality Control by Artificial Vision 2015
Twelfth International Conference on Quality Control by Artificial Vision 2015, Jun 2015, Le Creusot, France. ⟨10.1117/12.2182865⟩
QCAV, Jun 2015, Le Creusot, France
Twelfth International Conference on Quality Control by Artificial Vision 2015
Twelfth International Conference on Quality Control by Artificial Vision 2015, Jun 2015, Le Creusot, France. ⟨10.1117/12.2182865⟩
International audience; Image decomposition into structures and texture components appears as major objectives in image analysis. Following to Yves Meyer works that are based on Total Variation (VT), the decomposition model has been a renewed interes
Autor:
Bertrand Augereau, Benoit Tremblais
Publikováno v:
Pattern Recognition Letters. 25:603-618
In this paper we present a new explicit numerical scheme to approximate the solution of the linear diffusion filtering. This scheme is fast, stable, easy to program, applicable to arbitrary dimensions, and preserves the discontinuities of the objects
Publikováno v:
ICASSP
Proceedings of International Conference on Acoustics, Speech, and Signal Processing-IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014, Florence, Italy. pp.529
Proceedings of International Conference on Acoustics, Speech, and Signal Processing-IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014, Florence, Italy. pp.529
International audience; In this paper, we propose a new polynomial based texture representation method for extracting information about facial expressions. While many appearance-based methods have been proposed over the years to improve the performan
Publikováno v:
Pattern Recognition Letters. 22:759-768
A new method for invariant feature extraction on textured images undergoing affine transformations is presented. This is performed by transformation of the autocorrelation function (ACF) followed by determination of an invariant criterion which is th
Publikováno v:
Neural Processing Letters. 5:19-24
We introduce a new analysis tool able to test the learning distribution inside an MLP network. This tool is based on the exploitation of specific indicators which measure the contribution of any interconnection graph subset to the information gain ev
Publikováno v:
17th IEEE International Conference on Image Processing (ICIP) 2010
International Conference on Image Processing (ICIP) 2010
International Conference on Image Processing (ICIP) 2010, Sep 2010, Hong-Kong, China. pp.2469-2472
ICIP
HAL
International Conference on Image Processing (ICIP) 2010
International Conference on Image Processing (ICIP) 2010, Sep 2010, Hong-Kong, China. pp.2469-2472
ICIP
HAL
International audience; In this paper we propose a new descriptor for human motion analysis. We try to recognize human motion represented by sequence of vector fields which are obtained with optical flow. Our method is based on an efficient measure o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1cfc74d0146919212986d2dc2df47ade
https://hal.archives-ouvertes.fr/hal-00594762
https://hal.archives-ouvertes.fr/hal-00594762
Autor:
David Helbert, Bertrand Augereau
Publikováno v:
[Research Report] Université de poitiers. 2010
HAL
HAL
We describe a reconstruction method of three dimensional marker trajectories from several cameras in the applicative framework of sportive gesture analysis. The principle is to apply a tracking algorithm on extracted markers from each sequence of ima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ff9872e4eb06e2de2b1ae26a95f27e58
https://hal.archives-ouvertes.fr/hal-02078393
https://hal.archives-ouvertes.fr/hal-02078393