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.

公开(公告)号：US20240338833A1

公开(公告)日：2024-10-10

申请号：US18296939

申请日：2023-04-06

Applicant: Lawrence Livermore National Security, LLC

Inventor： David Chambers ,  Jeffrey Edward Mast

IPC: G06T7/30 ,  G06T5/40 ,  G06T5/50 ,  G06V10/44 ,  G06V10/46 ,  G06V10/50 ,  G06V10/60 ,  G06V10/74

CPC classification number: G06T7/30 ,  G06T5/40 ,  G06T5/50 ,  G06V10/44 ,  G06V10/462 ,  G06V10/50 ,  G06V10/60 ,  G06V10/761 ,  G06T2207/10044

Abstract: A method of coregistering images is disclosed. Two dimensional images are first preprocessed, including clipping values in each image to a specified standard value range, and then applying a local equalization technique to the clipped images. Feature extraction is then performed to identify one or more features in the images. One or more of the extracted features are then matched between images to determine a degree of overlap between the images and a relationship between image coordinates of the images. The images are then transformed to a common coordinate system based on the degree of overlap and the relationship between their image coordinates. The images are then combined to form a single image.

公开(公告)号：US12106588B2

公开(公告)日：2024-10-01

申请号：US18594423

申请日：2024-03-04

Applicant: Beckman Coulter, Inc.

Inventor： Takayuki Mizutani ,  Katsuhiro Seo ,  Shigeru Fujii ,  Kazuki Umebara ,  MArie Willette ,  Leila Nazemi

IPC: G06V20/69 ,  C12M1/34 ,  G06T7/62 ,  G06V10/50 ,  G06V20/50

CPC classification number: G06V20/69 ,  C12M41/46 ,  G06T7/62 ,  G06V10/50 ,  G06V20/50 ,  G06T2207/10024 ,  G06T2207/30072

Abstract: Automatic substance preparation and evaluation systems and methods are provided for preparing and evaluating a fluidic substance, such as e.g. a sample with bodily fluid, in a container and/or in a dispense tip. The systems and methods can detect volumes, evaluate integrities, and check particle concentrations in the container and/or the dispense tip.

公开(公告)号：US12062088B1

公开(公告)日：2024-08-13

申请号：US17539641

申请日：2021-12-01

Applicant: UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)

Inventor： Reynaldo Medina ,  Bharat Prasad

IPC: G06Q40/02 ,  G06Q20/04 ,  G06Q20/10 ,  G06T5/40 ,  G06T7/11 ,  G06T7/12 ,  G06V10/10 ,  G06V10/20 ,  G06V10/44 ,  G06V10/50 ,  G06V20/62 ,  G06V30/416 ,  H04N1/40 ,  H04N23/00

CPC classification number: G06Q40/02 ,  G06Q20/042 ,  G06Q20/0425 ,  G06Q20/1085 ,  G06T5/40 ,  G06T7/11 ,  G06T7/12 ,  G06V10/10 ,  G06V10/20 ,  G06V10/443 ,  G06V10/50 ,  G06V20/63 ,  G06V30/416 ,  H04N1/40012 ,  H04N23/00 ,  G06T2207/20132

Abstract: The present application is directed to apparatuses, methods, and systems for remote deposit capture with enhanced image detection. In one form, a system includes a processor configured to extract an instrument image from an image that is associated with an account, where the instrument image is extracted by determining at least one corner of a plurality of corners of an instrument in the image, and to transmit the instrument image to a financial institution server to transfer funds between financial institution accounts.

公开(公告)号：US12054162B2

公开(公告)日：2024-08-06

申请号：US17594152

申请日：2019-04-05

Applicant: VOLVO TRUCK CORPORATION

Inventor： Leo Laine ,  Mats Jonasson

IPC: B60W50/00 ,  B60W30/14 ,  G06T7/90 ,  G06V10/50 ,  G06V20/56

CPC classification number: B60W50/0097 ,  B60W30/143 ,  G06T7/90 ,  G06V10/50 ,  G06V20/588 ,  B60W2420/403 ,  B60W2552/40 ,  B60W2555/20 ,  B60W2720/106 ,  B60W2720/30 ,  G06T2207/10024 ,  G06T2207/30256

Abstract: The invention relates to a method for determining a parameter indicative of a road capability of a road segment (16) supporting a vehicle (10). The vehicle (10) comprises a sensor (18) adapted to generate an information package on the basis of signals (20, 22) reflected from the surface of a portion of the road segment (16) in front of the vehicle (10), as seen in an intended direction of travel of the vehicle (10). The vehicle (10) further comprises a plurality of ground engaging members (12, 14). The method comprises: —determining a reference content measure indicative of the information content of an information package supplied by the sensor (18) at a reference time instant (T1); —comparing the reference content measure to a previous content measure indicative of the information content of an information package supplied by the sensor (18) at a previous time instant (T0), the previous time instant (T0) occurring before the reference time instant (T1); —upon detecting that a difference between the reference content measure and the previous content measure is outside a predetermined tolerance range, allowing the execution of a determination procedure for determining the parameter indicative of the road capability of the road segment (16) supporting the vehicle (10); —upon detecting that the difference between the reference content measure and the previous content measure is within the predetermined tolerance range, not allowing the execution of the determination procedure, and —wherein the determination procedure comprises modifying the operation of one or more of the ground engaging members (12, 14).

公开(公告)号：US11985365B2

公开(公告)日：2024-05-14

申请号：US17760898

申请日：2020-08-06

Applicant: SONY GROUP CORPORATION

Inventor： Takayoshi Shimizu

IPC: H04N21/234 ,  G06V10/74 ,  G06V10/60 ,  G06V10/50 ,  H04N21/6587

CPC classification number: H04N21/23424 ,  G06V10/50 ,  G06V10/60 ,  G06V10/761 ,  H04N21/6587

Abstract: There is provided a device and method for playing back a performer reaction image frame in response to a user action on playback content, the performer reaction image frame including a scene of the performer in reaction. In a case where a user action on the playback content is detected and the user action is detected, a playback image frame in the playback content is replaced with a performer reaction image frame including a scene of a performer in reaction, and the performer reaction image frame is played back. A data processing unit calculates a similarity rate between the playback image frame at a time of detection of the user action and a performer reaction image frame, and selects and plays back a performer reaction image frame of which calculated similarity rate is equal to or higher than a predetermined threshold value.

公开(公告)号：US20240119705A1

公开(公告)日：2024-04-11

申请号：US18285506

申请日：2022-04-01

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： Jing Ping Xu ,  Jiayin Zhou ,  Jun Ping Deng ,  William Tao Shi ,  Hua Xie

IPC: G06V10/764 ,  A61B8/08 ,  G06T7/00 ,  G06T7/11 ,  G06T7/143 ,  G06T7/174 ,  G06T11/00 ,  G06V10/22 ,  G06V10/26 ,  G06V10/50 ,  G06V10/82 ,  G16H50/20

CPC classification number: G06V10/764 ,  A61B8/08 ,  A61B8/5223 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/143 ,  G06T7/174 ,  G06T11/00 ,  G06V10/235 ,  G06V10/267 ,  G06V10/50 ,  G06V10/82 ,  G16H50/20 ,  G06T2207/10016 ,  G06T2207/10132 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20104 ,  G06T2207/30056 ,  G06V2201/031

Abstract: An ultrasound imaging system may acquire an image of a liver. The liver may be segmented from the image. Parameters, such as image homogeneity map, intensity probability chart, and/or speckle size diagram, may be extracted from the liver portion of the image. The parameters may be used to determine whether fatty liver deposits are diffuse or inhomogeneous. In some examples, inhomogeneous regions may be excluded from the calculation of liver fat quantification measurements. In some examples, the inhomogeneous regions may be displayed so that a user may select a region of interest that excludes the inhomogeneous regions to calculate the liver fat quantification measurements.

公开(公告)号：US11954925B2

公开(公告)日：2024-04-09

申请号：US17682809

申请日：2022-02-28

Applicant: Beckman Coulter, Inc.

Inventor： Takayuki Mizutani ,  Katsuhiro Seo ,  Shigeru Fujii ,  Kazuki Umebara

IPC: G06V20/69 ,  C12M1/34 ,  G06T7/62 ,  G06V10/50 ,  G06V20/50

CPC classification number: G06V20/69 ,  C12M41/46 ,  G06T7/62 ,  G06V10/50 ,  G06V20/50 ,  G06T2207/10024 ,  G06T2207/30072

Abstract: Automatic substance preparation and evaluation systems and methods are provided for preparing and evaluating a fluidic substance, such as e.g. a sample with bodily fluid, in a container and/or in a dispense tip. The systems and methods can detect volumes, evaluate integrities, and check particle concentrations in the container and/or the dispense tip.

公开(公告)号：US11921818B2

公开(公告)日：2024-03-05

申请号：US17330495

申请日：2021-05-26

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Seoul National University R&DB Foundation

Inventor： Jang-Hyun Kim ,  Hyun Oh Song ,  Wonho Choo ,  Seungyong Moon ,  Gaon An ,  Hosan Jeong

IPC: G06F18/214 ,  G06V10/50 ,  H04N1/60

CPC classification number: G06F18/2148 ,  G06V10/50 ,  H04N1/6063

Abstract: A method includes obtaining a color transformation matrix that removes color distortion of an original color histogram of a target color space for an input image of an original color space; obtaining a color transformation image of the original color space from which color distortion of the input image is removed using the color transformation matrix; and obtaining a space transformation image with a minimum target loss value between an output vector of a neural network for one of candidate images and each of a plurality of candidate class vectors of the input image, the candidate images being spaced apart from the color transformation image of the original color space by a distance less than a threshold.

公开(公告)号：US20240062410A1

公开(公告)日：2024-02-22

申请号：US17891185

申请日：2022-08-19

Applicant: Honda Motor Co., Ltd.

Inventor： Alireza REZAZADEH ,  Nawid JAMALI ,  Soshi IBA

IPC: G06T7/73 ,  G06T7/55 ,  G06T7/11 ,  G06V10/50

CPC classification number: G06T7/73 ,  G06T7/55 ,  G06T7/11 ,  G06V10/50 ,  G06T2207/20016 ,  G06T2207/10028 ,  G06T2207/10024 ,  G06T2207/20132 ,  G06T2207/20081

Abstract: A system and method for multimodal object-centric representation learning that include receiving data associated with an image and a depth map of an object. The system and method also include determining an object-surface point cloud based on the image and the depth map. The system and method additionally include determining multi-resolution receptive fields based on the object-surface point cloud. The system and method further include passing the multi-resolution receptive fields through convolutional encoders to learn an object centric representation of the object.