-
公开(公告)号：US20250071245A1
公开(公告)日：2025-02-27
申请号：US18943043
申请日：2024-11-11
Applicant: B1 INSTITUTE OF IMAGE TECHNOLOGY, INC.
Inventor： Ki Baek KIM
IPC: H04N13/161 , G06T3/40 , H04N19/103 , H04N19/105 , H04N19/11 , H04N19/119 , H04N19/124 , H04N19/129 , H04N19/13 , H04N19/134 , H04N19/159 , H04N19/167 , H04N19/172 , H04N19/176 , H04N19/597 , H04N19/625 , H04N19/70 , H04N23/698
Abstract: Disclosed are methods and apparatuses for decoding an image. A method includes receiving a bitstream obtained by encoding the image; dividing a first coding block into a plurality of second coding blocks; generating a prediction block of a second coding block based on syntax information obtained from the bitstream; and reconstructing the second coding block based on the prediction block and a residual block of the second coding block, the residual block being obtained by performing a dequantization and an inverse-transform on quantized transform coefficients from the bitstream. The first coding block has a recursive division structure. The first coding block is divided based on at least one of a quad tree division, a binary tree division or a triple tree division.
-
公开(公告)号：US20250069186A1
公开(公告)日：2025-02-27
申请号：US18943110
申请日：2024-11-11
Applicant: Snap Inc.
Inventor： Bernhard Jung , Edward Lee Kim-Koon
Abstract: A method for adjusting an over-rendered area of a display in an AR device is described. The method includes identifying an angular velocity of a display device, a most recent pose of the display device, previous warp poses, and previous over-rendered areas, and adjusting a size of a dynamic over-rendered area based on a combination of the angular velocity, the most recent pose, the previous warp poses, and the previous over-rendered areas.
-
公开(公告)号：US12236592B2
公开(公告)日：2025-02-25
申请号：US17944881
申请日：2022-09-14
Inventor： Nahid Ul Islam , Shiv Gehlot , Zongwei Zhou , Jianming Liang
Abstract: Described herein are means for systematically determining an optimal approach for the computer-aided diagnosis of a pulmonary embolism, in the context of processing medical imaging. According to a particular embodiment, there is a system specially configured for diagnosing a Pulmonary Embolism (PE) within new medical images which form no part of the dataset upon which the AI model was trained. Such a system executes operations for receiving a plurality of medical images and processing the plurality of medical images by executing an image-level classification algorithm to determine the presence or absence of a Pulmonary Embolism (PE) within each image via operations including: pre-training an AI model through supervised learning to identify ground truth; fine-tuning the pre-trained AI model specifically for PE diagnosis to generate a pre-trained PE diagnosis and detection AI model; wherein the pre-trained AI model is based on a modified CNN architecture having introduced therein a squeeze and excitation (SE) block enabling the CNN architecture to extract informative features from the plurality of medical images by fusing spatial and channel-wise information; applying the pre-trained PE diagnosis and detection AI model to new medical images to render a prediction as to the presence or absence of the Pulmonary Embolism within the new medical images; and outputting the prediction as a PE diagnosis for a medical patient.
-
公开(公告)号：US12236586B2
公开(公告)日：2025-02-25
申请号：US17587688
申请日：2022-01-28
Applicant: 2692873 Ontario Inc.
Inventor： Trevor Champagne
Abstract: Systems and methods using machine learning for classifying images as being sufficient for medical diagnosis. An example of the method includes: receiving a dataset comprising a plurality of medical images; receiving, from a first single source, a respective label for each one of the plurality of medical images, the respective label being a positive response versus a negative response; dividing each one of the plurality of medical images into a plurality of medical image segments; associating each one of the plurality of medical image segments with an image segment label based on the respective label for the respective medical image being divided; and training a machine learning model using: the plurality of medical images, the respective label for each one of the plurality of medical images, the plurality of medical image segments, and the respective image segment label of each one of the plurality of medical image segments.
-
公开(公告)号：US12236557B2
公开(公告)日：2025-02-25
申请号：US17877274
申请日：2022-07-29
Applicant: SEIKO EPSON CORPORATION
Inventor： Naoki Suzuki
Abstract: A display apparatus controlling method includes accepting input of a first image signal representing a first image, generating a second image signal by applying a first process of rotating the first image to the first image signal in accordance with the amount of rotation of the display apparatus calculated based on an output signal from an inertial sensor fixed to the display apparatus, and displaying on a display surface a display image corresponding to a second image based on the second image signal.
-
Patent Agency Ranking
公开(公告)号：US12236504B2
公开(公告)日：2025-02-25
申请号：US18533828
申请日：2023-12-08
Applicant: Xero Limited
Inventor： Diego Granados Diaz , Hayden Thomas Doward
IPC: G06T11/20 , G06F3/0482 , G06T3/20 , G06T3/40 , G06T3/60
Abstract: A graphical user interface for display on a display screen of a user device is configured for display in a window occupying all or a portion of the display screen and has a first frame occupying a first frame region of the window. The first frame illustrates, adjacent to one another in a first dimension, graph visual elements each representing a respective graph data entry from a continuous subset among a sequence of graph data entries, each of the sequence having a defined placement and a quantitative value. The continuous subset is determined in response to selective zooming and/or scrolling of the first frame region by user interaction. The graph visual elements each have, in a second dimension, a linear extent or position determined according to the size of the first frame region in the second dimension, the quantitative value of the respective graph data entry, and dynamic scaling factor.
-
公开(公告)号：US12236154B2
公开(公告)日：2025-02-25
申请号：US18545350
申请日：2023-12-19
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yongjin Kwon , Hyoyeon Kim , Wooyoung Park , Sukjae Lee , Byungseok Jung , Seonghoon Choi , Jongwu Baek
IPC: G06F3/14 , G06F1/16 , G06F3/041 , G06F3/0485 , G06F3/0488 , G06F3/04883 , G06F3/04886 , G06F9/451 , G06T3/40 , H04M1/02
Abstract: A mobile communication device is provided. The mobile communication includes a first touch display forming a portion of a first surface of the mobile communication device, a second touch display forming a portion of a second surface of the mobile communication device, and a processor configured to display in the first touch display a first screen corresponding to an application executed in a first folding state while a state of the device is the first folding state, identify the state of the mobile communication device changing to a second folding state, and display in the second touch display, based on the identification, a second screen corresponding to the application and an image partially overlapping the second screen, a touch input on the second touch display while the second screen and the image are displayed in the second touch display as overlapping is configured to not be processed as an input.
-
公开(公告)号：US12235677B2
公开(公告)日：2025-02-25
申请号：US18214696
申请日：2023-06-27
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Saar Shai
Abstract: Disclosed are devices which include flexible display sheets or other flexible elements, whereas by physically manipulating said flexible display sheets or elements, interaction with said device may be facilitated. Flexibility features may be employed to provide methods of interaction which include manipulating flexible section. Some of said methods of interaction are disclosed. Further disclosed are units which can connect to flexible display sheets, for interacting with said flexible display sheets.
-
公开(公告)号：US12231827B2
公开(公告)日：2025-02-18
申请号：US18122975
申请日：2023-03-17
Applicant: SEIKO EPSON CORPORATION
Inventor： Yohei Aoki
Abstract: A display method includes: acquiring information representing a size of a projection area of a projector; acquiring an input image including a person; generating information representing a size of a face of the person included in the input image, based on the information representing the size of the projection area; correcting the input image in such a way that the size of the face of the person included in the input image becomes closer to life size in the projection area, based on the information representing the size of the face of the person; generating projection image data representing a projection image including the input image; and displaying the projection image in the projection area, based on the projection image data.
-
公开(公告)号：US20250054134A1
公开(公告)日：2025-02-13
申请号：US18447213
申请日：2023-08-09
Applicant: UTI LIMITED PARTNERSHIP
Inventor： Behrouz Far , Trafford Crump , Ezekiel Weis , Emad A. Mohammed
Abstract: Methods and systems are described for detecting ocular lesions indicative of an ocular pathology. The methods and systems involve obtaining a fundus image of an eye of a patient, preprocessing the fundus image to obtain a processed fundus image applying a detection model to the processed fundus image to identify whether a lesion is present in the fundus image providing an output based on an output result of the detection model. The detection model is configured for detecting ocular lesions in fundus images and the output is related to a lesion being present in the fundus image.
-
-
-
-
-
-
-
-
-
Search Results
17157
records
(took 0.044 seconds)
