-
公开(公告)号：US12118721B2
公开(公告)日：2024-10-15
申请号：US18100543
申请日：2023-01-23
Applicant: Owkin Inc. , Owkin France SAS
Inventor： Pierre Courtiol , Olivier Moindrot , Charles Maussion , Charlie Saillard , Benoit Schmauch , Gilles Wainrib
IPC: G06T7/00 , G06F18/21 , G06F18/214 , G06F18/23 , G06F18/2413 , G06N3/04 , G06T7/11 , G06T7/194 , G06V10/32 , G06V10/50 , G06V10/764 , G06V10/82 , G06V20/69
CPC classification number: G06T7/0012 , G06F18/214 , G06F18/2163 , G06F18/217 , G06F18/23 , G06F18/2413 , G06N3/04 , G06T7/11 , G06T7/194 , G06V10/32 , G06V10/50 , G06V10/764 , G06V10/82 , G06V20/695 , G06V20/698 , G06T2207/10056 , G06T2207/20081 , G06T2207/20084 , G06T2207/30024
Abstract: A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the device segments the image into a region of interest that includes information useful for classification and a background region by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.
-
Patent Agency Ranking
公开(公告)号：US20230386024A1
公开(公告)日：2023-11-30
申请号：US18100543
申请日：2023-01-23
Applicant: Owkin Inc. , Owkin France SAS
Inventor： Pierre Courtiol , Olivier Moindrot , Charles Maussion , Charlie Saillard , Benoit Schmauch , Gilles Wainrib
IPC: G06T7/00 , G06T7/194 , G06T7/11 , G06N3/04 , G06V20/69 , G06V10/50 , G06V10/82 , G06V10/764 , G06F18/23 , G06F18/214 , G06F18/21 , G06F18/2413 , G06V10/32
CPC classification number: G06T7/0012 , G06T7/194 , G06T7/11 , G06N3/04 , G06V20/695 , G06V10/50 , G06V20/698 , G06V10/82 , G06V10/764 , G06F18/23 , G06F18/214 , G06F18/217 , G06F18/2163 , G06F18/2413 , G06V10/32 , G06T2207/10056 , G06T2207/20081 , G06T2207/20084 , G06T2207/30024
Abstract: A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the device segments the image into a region of interest that includes information useful for classification and a background region by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.
-
公开(公告)号：US11562585B2
公开(公告)日：2023-01-24
申请号：US17183329
申请日：2021-02-23
Applicant: Owkin Inc. , Owkin France SAS
Inventor： Pierre Courtiol , Olivier Moindrot , Charles Maussion , Charlie Saillard , Benoit Schmauch , Gilles Wainrib
IPC: G06V20/69 , G06T7/194 , G06T7/11 , G06K9/62 , G06T7/00 , G06V10/50 , G06V10/82 , G06V10/764 , G06N3/04 , G06V10/32
Abstract: A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the device segments the image into a region of interest that includes information useful for classification and a background region by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.
-
公开(公告)号：US20210256699A1
公开(公告)日：2021-08-19
申请号：US17185924
申请日：2021-02-25
Applicant: Owkin Inc. , Owkin France SAS , Centre Léon Bérard
Inventor： Gilles Wainrib , Thomas Clozel , Pierre Courtiol , Charles Maussion , Jean-Yves Blay , Françoise Galateau Sallé
Abstract: A method and apparatus of a device that classifies a mesothelioma image is described. In an exemplary embodiment, the device segments the mesothelioma image into a region of interest that includes information useful for classification, and a background region, by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.
-
公开(公告)号：US11544851B2
公开(公告)日：2023-01-03
申请号：US17185924
申请日：2021-02-25
Applicant: Owkin Inc. , Owkin France SAS , Centre Léon Bérard
Inventor： Gilles Wainrib , Thomas Clozel , Pierre Courtiol , Charles Maussion , Jean-Yves Blay , Françoise Galateau Sallé
Abstract: A method and apparatus of a device that classifies a mesothelioma image is described. In an exemplary embodiment, the device segments the mesothelioma image into a region of interest that includes information useful for classification, and a background region, by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.
-
公开(公告)号：US20210271847A1
公开(公告)日：2021-09-02
申请号：US17183329
申请日：2021-02-23
Applicant: Owkin Inc. , Owkin France SAS
Inventor： Pierre Courtiol , Olivier Moindrot , Charles Maussion , Charlie Saillard , Benoit Schmauch , Gilles Wainrib
Abstract: A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the device segments the image into a region of interest that includes information useful for classification and a background region by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.
-
-
-
-
-
Search Results
6
records
(took 0.021 seconds)
