公开(公告)号：US12236560B2

公开(公告)日：2025-02-25

申请号：US17686059

申请日：2022-03-03

Applicant: Apple Inc.

Inventor： Jack Greasley

IPC: G06K9/00 ,  G06K9/32 ,  G06T5/20 ,  G06T5/75 ,  G06T7/30 ,  G06T11/00

Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

公开(公告)号：US12125273B2

公开(公告)日：2024-10-22

申请号：US17510407

申请日：2021-10-26

Applicant: Axis AB

Inventor： Björn Ardö ,  Anton Jakobsson

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/32 ,  G06K9/46 ,  G06V10/147 ,  G06V10/25 ,  G06V10/46 ,  G06V10/94

CPC classification number: G06V10/95 ,  G06V10/147 ,  G06V10/25 ,  G06V10/462

Abstract: A method (100), a device (600;700) and a system (800) for processing image data representing a scene for extracting features related to objects in the scene using a convolutional neural network are disclosed. Two or more portions of the image data representing a respective one of two or more portions of the scene are processed (S110), by means of a respective one of two or more circuitries, through a first number of layers of the convolutional neural network to form two or more outputs, wherein the two or more portions of the scene are partially overlapping. The two or more outputs are combined (S120) to form a combined output, and the combined output is processed (S130) through a second number of layers of the convolutional neural network by means of one of the two or more circuitries for extracting features related to objects in the scene.

公开(公告)号：US12059579B2

公开(公告)日：2024-08-13

申请号：US16979619

申请日：2019-03-07

Applicant: Toshiba Energy Systems & Solutions Corporation

Inventor： Kenichi Karasawa ,  Ryusuke Hirai ,  Tomoya Okazaki ,  Yasunori Taguchi ,  Keiko Okaya ,  Shinichiro Mori

IPC: A61N5/10 ,  A61B6/00 ,  A61B6/46 ,  G06F3/14 ,  G06K9/32 ,  G06T7/00 ,  G06T7/70 ,  G06T11/00

CPC classification number: A61N5/1049 ,  A61B6/463 ,  A61B6/487 ,  A61N5/1037 ,  G06F3/14 ,  G06T7/0012 ,  G06T7/70 ,  G06T11/003 ,  G06T2207/10064 ,  G06T2207/10081 ,  G06T2207/10124 ,  G06T2207/30096

Abstract: A medical image processing device includes a region-of-interest acquirer, a treatment plan acquirer, a degree-of-influence calculator, and a display controller. The region-of-interest acquirer is configured to acquire a partial region within a body of a patient as a region of interest. The treatment plan acquirer is configured to acquire treatment plan information determined in a planning stage of radiation treatment to be performed on the patient. The degree-of-influence calculator is configured to calculate a degree of influence representing an influence on the region of interest up to a range until radiation with which the patient is irradiated reaches a target portion to be treated within the body of the patient. The display controller is configured to generate a display image in which information regarding the degree of influence is superimposed on a current fluoroscopic image of the patient and causes a display to display the display image.

公开(公告)号：US12036084B2

公开(公告)日：2024-07-16

申请号：US17322164

申请日：2021-05-17

Applicant: Align Technology, Inc.

Inventor： Srinivas Kaza ,  Bob Grove

IPC: G06K9/00 ,  A61B34/10 ,  A61C7/00 ,  A61C7/08 ,  A61C9/00 ,  A61C11/00 ,  G06K9/32 ,  G06K9/36 ,  G16B5/00 ,  G16H50/50 ,  G16Z99/00

CPC classification number: A61C7/002 ,  A61B34/10 ,  A61C7/08 ,  A61C9/00 ,  A61C9/0006 ,  A61C9/0046 ,  A61C9/0053 ,  G16B5/00 ,  G16H50/50 ,  G16Z99/00

Abstract: Method and system for managing multiple impressions of a patient's jaw for an orthodontic treatment are provided. The method includes scanning at least a first impression and a second impression of the same jaw for the orthodontic treatment; determining if the first jaw impression and the second jaw impression have distortion in different areas; selecting the first jaw impression or the second jaw impression as a base impression; and replacing distorted tooth data from the base impression with data for the same tooth from a non-base impression. The method also includes scanning at least a first jaw impression for the orthodontic treatment; scanning a bite impression for the orthodontic treatment; matching the scanned first jaw impression with the scanned bite impression; comparing bite information with a tooth occlusal surface; and determining if reconstruction is to be performed on the tooth occlusal surface.

公开(公告)号：US11945169B2

公开(公告)日：2024-04-02

申请号：US17332511

申请日：2021-05-27

Applicant: XEROX CORPORATION

Inventor： Vijay Kumar Baikampady Gopalkrishna ,  Raja Bala ,  Palghat Ramesh ,  David Allen Mantell ,  Peter Michael Gulvin ,  Mark A. Cellura

IPC: B29C64/393 ,  B29C64/112 ,  B29C64/209 ,  B33Y30/00 ,  B33Y50/02 ,  G06K9/32 ,  G06T7/13 ,  G06T7/70 ,  G06V10/20

CPC classification number: B29C64/393 ,  B29C64/112 ,  B29C64/209 ,  B33Y30/00 ,  B33Y50/02 ,  G06T7/13 ,  G06T7/70 ,  G06V10/255

Abstract: A 3D printer includes a nozzle configured to jet a drop of liquid metal therethrough. The 3D printer also includes a light source configured to illuminate the drop with a pulse of light. A duration of the pulse of light is from about 0.0001 seconds to about 0.1 seconds. The 3D printer also includes a camera configured to capture an image, video, or both of the drop. The 3D printer also includes a computing system configured to detect the drop in the image, the video, or both. The computing system is also configured to characterize the drop after the drop is detected. Characterizing the drop includes determining a size of the drop, a location of the drop, or both in the image, the video, or both.

公开(公告)号：US11937897B2

公开(公告)日：2024-03-26

申请号：US17849074

申请日：2022-06-24

Applicant: AI Biomed Corp. ,  Vanderbilt University

Inventor： Adnan Abbas ,  Melanie McWade ,  Anita Mahadevan-Jansen

IPC: A61B5/00 ,  A61B90/00 ,  G06K9/32 ,  G06V10/145 ,  G06V10/25

CPC classification number: A61B5/0037 ,  A61B5/7445 ,  A61B90/361 ,  G06V10/145 ,  G06V10/25 ,  A61B5/0071 ,  A61B2090/366

Abstract: Devices and methods for visibly highlighting areas of a region including an imager configured to image the region with a sensitivity to at least one of wavelength, light level, or contrast greater than the human eye, an overlay element configured to visibly highlight areas of the region and registered to the imager to produce alignment of imaged features with highlighted features at the same location on the region, and at least one of a controller executing a program or logic configured to process acquired images from the imager to identify areas of the region determined not visible to the human eye, and control the overlay element to visibly highlight those areas on the region.

公开(公告)号：US11847806B2

公开(公告)日：2023-12-19

申请号：US17153359

申请日：2021-01-20

Applicant: Dell Products, L.P.

Inventor： Lee Daniel Saeugling

IPC: G06K9/20 ,  G06K9/32 ,  G06K9/62 ,  G06N3/08 ,  G06V10/22 ,  G06V10/25 ,  G06V10/24 ,  G06F18/214 ,  G06F18/21 ,  G06F40/166 ,  G06V30/10

CPC classification number: G06V10/23 ,  G06F18/214 ,  G06F18/2163 ,  G06N3/08 ,  G06V10/242 ,  G06V10/25 ,  G06F40/166 ,  G06V30/10

Abstract: Scene text information extraction of desired text information from an image can be performed and managed. An information management component (IMC) can determine an anchor word based on analysis of an image. To facilitate determining desired text information in the image, IMC can re-orient the image to zero or substantially zero degrees if it determines that the orientation is skewed. IMC can utilize a neural network to determine and apply bounding boxes to text strings in the image. Using a rules-based approach or machine learning techniques, employing a trained machine learning component, IMC can utilize the anchor word along with inline grouping of textual information in the image, deep text recognition analysis, or bounding box prediction to determine or predict the desired text information in the image. IMC can facilitate presenting the desired text information, anchor word, or other information obtained from the image in an editable format.

公开(公告)号：US11847188B2

公开(公告)日：2023-12-19

申请号：US17189156

申请日：2021-03-01

Applicant: Shenzhen Imsight Medical Technology Co., Ltd.

Inventor： Hao Chen ,  Yu Hu ,  Zhizhong Chai ,  Guangwu Qian

IPC: G06K9/62 ,  G06K9/32 ,  G06T7/00 ,  G06N3/08 ,  G06F18/2431 ,  G06V10/20

CPC classification number: G06F18/2431 ,  G06N3/08 ,  G06T7/0012 ,  G06V10/255 ,  G06T2207/10116 ,  G06T2207/30064 ,  G06T2207/30096

Abstract: A method includes the following steps: pre-processing chest X-ray films to obtain initial X-ray film images that meets format requirements; screening the initial X-ray film images to detect whether they are posteroanterior chest images; inputting the posteroanterior chest images into a binary classification model of the deep convolutional neural network for negative and positive classification; inputting the images presenting positive results into a detection model of the deep convolutional neural network to detect a disease type and label an outline of a lesion area in each image; and displaying the disease type and lesion area corresponding to the image.

公开(公告)号：US11783086B2

公开(公告)日：2023-10-10

申请号：US17887998

申请日：2022-08-15

Applicant: Movidius Ltd.

Inventor： David Moloney

IPC: G06T5/00 ,  G06F21/84 ,  G06K9/32 ,  G06K9/46 ,  G06F21/62 ,  G06N5/00 ,  H04W4/02 ,  G06V20/58 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44 ,  G06V20/00 ,  G06V20/52 ,  G06V40/16

CPC classification number: G06F21/6254 ,  G06F21/84 ,  G06N5/00 ,  G06T5/002 ,  G06T5/004 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/00 ,  G06V20/52 ,  G06V20/584 ,  H04W4/023 ,  G06V40/161

Abstract: An example stationary tracker includes memory to store fixed geographic location information indicative of a fixed geographic location of the stationary tracker, and to store a reference feature image; and at least one processor to: determine a feature in an image is a non-displayable feature by comparing the feature to the reference feature image; and generate a masked image, the masked image to mask the non-displayable feature based on the non-displayable feature not allowed to be displayed when captured from the fixed geographic location of the stationary tracker, and the masked image to display a displayable feature in the image; and a wireless interface to detect a wireless tag located on a tag bearer, the at least one processor to determine the tag bearer is the displayable feature in the image based on the wireless tag.

公开(公告)号：US11769226B2

公开(公告)日：2023-09-26

申请号：US17158553

申请日：2021-01-26

Applicant: KYOCERA Document Solutions Inc.

Inventor： Sheng Li ,  Dongpei Su

IPC: G06K9/00 ,  G06K9/32 ,  G06T3/40 ,  G06T1/20

CPC classification number: G06T3/4046 ,  G06T1/20 ,  G06T3/4053 ,  G06T3/4084

Abstract: Systems and methods upscale an input image by a final upscaling factor. The systems and methods employ a first module implementing a super resolution neural network with feature extraction layers and multiple sets of upscaling layers sharing the feature extraction layers. The multiple sets of upscaling layers upscale the input image according to different respective upscaling factors to produce respective first module outputs. The systems and methods select the first module output with the respective upscaling factor closest to the final upscaling factor. If the respective upscaling factor for the selected first module output is equal to the final upscaling factor, the systems and methods output the selected first module output. Otherwise, the systems and methods provide the selected first module output to a second module that upscales the selected first module output to produce a second module output corresponding to the input image upscaled by the final upscaling factor.