Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Petr Dokladal"'
Autor:
Eva Dejnožková, Petr Dokládal
Publikováno v:
Image Analysis and Stereology, Vol 22, Iss 2, Pp 121-132 (2011)
The computation of the distance function is a crucial and limiting element in many applications of image processing. This is particularly true for the PDE-based methods, where the distance is used to compute various geometric properties of the travel
Externí odkaz:
https://doaj.org/article/9751d7cb1247423aa0230fc0593e506d
Autor:
Juba Amrioui, Myriam Duc, Alain Le Kouby, Jeanne-Sylvine Guedon, Lucile Saussaye, Sahar Hemmati, François Willot, Petr Dokladal
Publikováno v:
Materials Today: Proceedings.
Publikováno v:
17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP'22)
17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP'22), Feb 2022, on-line, France
HAL
17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP'22), Feb 2022, on-line, France
HAL
International audience; In crack detection, pixel-accurate predictions are necessary to measure the width-an important indicator of the severity of a crack. However, manual annotation of images to train supervised models is a hard and time-consuming
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50d7c59c8c352ccb81869f517c40ea63
https://hal-upec-upem.archives-ouvertes.fr/hal-03451685
https://hal-upec-upem.archives-ouvertes.fr/hal-03451685
Publikováno v:
16th International Conference on Computer Vision Theory and Applications-VISAPP 2021
16th International Conference on Computer Vision Theory and Applications-VISAPP 2021, Feb 2021
Streaming, Austria
HAL
16th International Conference on Computer Vision Theory and Applications-VISAPP 2021, Feb 2021
Streaming, Austria
HAL
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::42b3382403dd24fde80e340f1f9fea29
https://hal-upec-upem.archives-ouvertes.fr/hal-03111509
https://hal-upec-upem.archives-ouvertes.fr/hal-03111509
Publikováno v:
British Machine Vision Conference (BMVC)
British Machine Vision Conference (BMVC), Sep 2019, Cardiff, United Kingdom
British Machine Vision Conference 2019, BMVC 2019
British Machine Vision Conference 2019, BMVC 2019, Sep 2019, Cardiff, United Kingdom
HAL
British Machine Vision Conference (BMVC), Sep 2019, Cardiff, United Kingdom
British Machine Vision Conference 2019, BMVC 2019
British Machine Vision Conference 2019, BMVC 2019, Sep 2019, Cardiff, United Kingdom
HAL
International audience; There are many measures of dissimilarity that, depending on the application, do not always have optimal behavior. In this paper, we present a qualitative analysis of the similarity measures most used in the literature and the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::65f01a58543a418ef28a150f6574c16d
https://hal-upec-upem.archives-ouvertes.fr/hal-02299826/document
https://hal-upec-upem.archives-ouvertes.fr/hal-02299826/document
Publikováno v:
HAL
In this work, we propose a new Convolutional Neural Network (CNN) for classification of rotated objects. This architecture is built around an ordered ensemble of oriented edge detectors to create a roto-translational space that transforms the input r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::91372415975f453f6370815dfdbe8e09
https://hal-enpc.archives-ouvertes.fr/hal-02170933/file/RotCNN.pdf
https://hal-enpc.archives-ouvertes.fr/hal-02170933/file/RotCNN.pdf
Publikováno v:
50th International Annual Conference of the Fraunhofer ICT
50th International Annual Conference of the Fraunhofer ICT, Jun 2019, Karlsruhe, Germany
HAL
50th International Annual Conference of the Fraunhofer ICT, Jun 2019, Karlsruhe, Germany
HAL
International audience; Impact experiments were performed at the french-german research Institute of Saint-Louis on three energetic materials composed of 70 % in weight of RDX particles embedded in a wax matrix. These materials differ by the microstr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::527b3deed888a142f9b3f10b7171e00d
https://hal.archives-ouvertes.fr/hal-02139566/document
https://hal.archives-ouvertes.fr/hal-02139566/document
Publikováno v:
HAL
42ème journée ISS France; Deep convolutional neural networks accuracy is heavily impacted by the rotations of the input data. In this paper, we propose a convolutional predictor that is invariant to rotations in the input. This architecture is capa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::05d6f659b206794ea340a556f79c8089
https://hal.science/hal-02022802
https://hal.science/hal-02022802
Publikováno v:
French-German Doctoral Workshop
French-German Doctoral Workshop, Nov 2018, Fontainebleau, France
HAL
French-German Doctoral Workshop, Nov 2018, Fontainebleau, France
HAL
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::addc703153f7985cd27ba01f74878141
https://hal.archives-ouvertes.fr/hal-01945673
https://hal.archives-ouvertes.fr/hal-01945673
Publikováno v:
Colloque MECAMAT 2018:Matériaux numériques. Microstructures et comportements thermomécanique
Colloque MECAMAT 2018:Matériaux numériques. Microstructures et comportements thermomécanique, 2018, Aussois, France
HAL
Colloque MECAMAT 2018:Matériaux numériques. Microstructures et comportements thermomécanique, 2018, Aussois, France
HAL
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0a7e94b3496c6d754befeeca476fd0a9
https://hal.archives-ouvertes.fr/hal-01678704
https://hal.archives-ouvertes.fr/hal-01678704