Výsledky vyhledávání - "Souheil Hadj Said"

Akademický článek

Complétion d'image exploitant des données multispectrales

Autor: Frédéric Bousefsaf, Mohamed Tamaazousti, Souheil Hadj Said, Rémi Michel

Publikováno v: Revue Française de Photogrammétrie et de Télédétection, Iss 215 (2017)

Nous proposons d'explorer le potentiel de l'imagerie multispectrale appliquée à la complétion d'image, une thématique classique de vision par ordinateur qui consiste à automatiquement remplacer une zone de l'image de manière plausible. Pour ce

Externí odkaz: https://doaj.org/article/7012000f28c74b788c6835e21e2a8d10

Zobrazit plný text záznamu

Image completion using multispectral imaging

Autor: Rémi Michel, Souheil Hadj Said, Frédéric Bousefsaf, Mohamed Tamaazousti

Publikováno v: IET Image Processing
IET Image Processing, 2018, 12 (7), pp.1164-1174. ⟨10.1049/iet-ipr.2017.1203⟩
IET Image Processing, Institution of Engineering and Technology, 2018, 12 (7), pp.1164-1174. ⟨10.1049/iet-ipr.2017.1203⟩

International audience; Abstract:Here, the authors explore the potential of multispectral imaging applied to image completion. Snapshot multispectral cameras correspond to breakthrough technologies that are suitable for everyday use. Therefore, they

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3a3ec1588c5649eab1fb3d3139c4711
https://cea.hal.science/cea-01836229

Zobrazit plný text záznamu

Color consistency of specular highlights in consumer cameras

Autor: Alexandre Morgand, John Lin, Souheil Hadj Said, Mohamed Tamaazousti

Publikováno v: the 23rd ACM Symposium on Virtual Reality Software and Technology
the 23rd ACM Symposium on Virtual Reality Software and Technology, Nov 2017, Gothenburg, Sweden. ⟨10.1145/3139131.3141216⟩
VRST

International audience; The latest advancements in Augmented Reality (AR) and Diminished Reality (DR) have allowed the development of many consumer-oriented applications (such as sales and driving aid, or education). To increase the realism in render

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7b983fd6ef135f8a0bd34f5d944befc3
https://hal-cea.archives-ouvertes.fr/cea-01836249

Zobrazit plný text záznamu

Complétion d'image exploitant des données multispectrales

Autor: Souheil Hadj Said, Rémi Michel, Mohamed Tamaazousti, Frédéric Bousefsaf

Publikováno v: Revue Française de Photogrammétrie et de Télédétection
Revue Française de Photogrammétrie et de Télédétection, 2017, 215, pp.65-79
Revue Française de Photogrammétrie et de Télédétection, Société Française de Photogrammétrie et de Télédétection, 2017, 215, pp.65-79
Revue Française de Photogrammétrie et de Télédétection, Iss 215 (2017)

International audience; Nous proposons d’explorer le potentiel de l’imagerie multispectrale appliquée à la complétion d’image, une thématiqueclassique de vision par ordinateur qui consiste à automatiquement remplacer une zone de l’image

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de5d6125265986c83d8e819f0d6a68dc
https://hal.science/hal-01850278

Zobrazit plný text záznamu

Image-Based Models for Specularity Propagation in Diminished Reality

Autor: Mohamed Tamaazousti, Souheil Hadj Said, Adrien Bartoli

Publikováno v: IEEE Transactions on Visualization and Computer Graphics
IEEE Transactions on Visualization and Computer Graphics, Institute of Electrical and Electronics Engineers, 2017, pp.1-1. ⟨10.1109/TVCG.2017.2705687⟩
IEEE Transactions on Visualization and Computer Graphics, 2017, pp.1-1. ⟨10.1109/TVCG.2017.2705687⟩

The aim of Diminished Reality (DR) is to remove a target object in a live video stream seamlessly. In our approach, the area of the target object is replaced with new texture that blends with the rest of the image. The result is then propagated to th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dee5d793db8b81c332fd54b112a79d4e
https://pubmed.ncbi.nlm.nih.gov/28541208

Zobrazit plný text záznamu

Multi-object recognition and tracking with feature points matching and spatial layout consistency

Autor: Ismail Boujelbane, Souheil Hadj Said, Titus Zaharia

Publikováno v: 2014 IEEE International Conference on Consumer Electronics-Berlin (ICCE-Berlin)
2014 IEEE International Conference on Consumer Electronics-Berlin (ICCE-Berlin), Sep 2014, Berlin, Germany. pp.355-359
ICCE-Berlin

In this paper, we propose a simultaneous textured object recognition and localization approach designed to real-time mobile devices applications. Local interest points are extracted and classified with the help of a strong matching algorithm. The mat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::72e5ffcfe57251663cc9c80625d29ba1
https://hal.archives-ouvertes.fr/hal-01111823

Zobrazit plný text záznamu

Recognition of urban buildings with spatial consistency and a small-sized vocabulary tree

Autor: Souheil Hadj Said, Titus Zaharia, Ismail Boujelbane

In this work, we address the problem of building recognition as a mobile application. Our approach exploits a small-sized vocabulary-tree of SIFT descriptors. Each SIFT descriptor in our dataset is saved along with its class label, its nearest neighb

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cd0aaca667de0d1ad32d0d32e396bd53
https://hal.archives-ouvertes.fr/hal-01111826

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání