Method and device for detecting display panel defect

    公开(公告)号:US12205269B2

    公开(公告)日:2025-01-21

    申请号:US17784073

    申请日:2021-06-11

    Abstract: A method for detecting a display panel defect, including: collecting a panel image of a to-be-detected display panel, a plurality of first pixels of the display panel corresponding to a plurality of second pixels in the panel image; converting the panel image into a binary image; dilating each bright spot region in the binary image such that adjacent bright spot regions communicate with each other to form at least one closed communication region in the binary image; determining a region of interest mask image in the binary image in accordance with the at least one closed communication region; determining a region of interest in accordance with the region of interest mask image and the panel image; and performing feature identification on the region of interest to determine a defect of the display panel.

    Method, device and system for sending virtual card, and readable storage medium

    公开(公告)号:US11917320B2

    公开(公告)日:2024-02-27

    申请号:US17437107

    申请日:2020-11-23

    CPC classification number: H04N5/272 G06V40/172 G10L17/06

    Abstract: Disclosed are a method, device and system for sending a virtual card and a readable storage medium, which are configured to receive at least one audio-video stream data of a plurality of participant terminals in communication connection with a server side; determine target audio-video stream data corresponding to at least one speaker from the at least one audio-video stream data; obtain biological characteristic information for identifying the at least one speaker from the target audio-video stream data, the biological characteristic information includes face characteristic information and/or voiceprint characteristic information; generate a virtual card according to the biological characteristic information; overlay the virtual card to the target audio-video stream data, and synthesize the target audio-video stream data with other audio-video stream data in response to there being a plurality of audio-video stream data into a to-be-sent audio-video stream data; send the to-be-sent audio-video stream data to the participant terminals.

    Method, apparatus and system for implementing video conference, and storage medium

    公开(公告)号:US12167160B2

    公开(公告)日:2024-12-10

    申请号:US17615881

    申请日:2020-10-30

    Abstract: Provided is a method for implementing a video conference. The method includes: acquiring layout information of a conference picture of the video conference, wherein the layout information comprises: information of at least two conferee regions in the conference picture, and information of corresponding relationships between the at least two conferee regions and at least two terminals involved in the video conference; sending the information of the corresponding conferee regions to the at least two terminals; receiving conferee multimedia data provided by the at least two terminals based on the information of the corresponding conferee regions; acquiring conference video data based on the conferee multimedia data; and sending the conference video data to the at least two terminals.

    MODEL TRAINING METHOD, PERFORMANCE PREDICTION METHOD, DEVICE, APPARATUS AND MEDIUM

    公开(公告)号:US20240303479A1

    公开(公告)日:2024-09-12

    申请号:US18021971

    申请日:2022-03-30

    CPC classification number: G06N3/08 G06N3/044

    Abstract: Disclosed is a model training method, a performance prediction method, an apparatus, a device and a medium, which relate to the technical field of display. The model training method includes acquiring a training sample set, wherein the training sample set includes: training design data and test data of a sample display device; inputting the training sample design data into a model to be trained, and training the model to be trained according to an output of the model to be trained and the training sample test data to obtain an initial prediction model; when the initial prediction model satisfies a pre-set condition, determining the initial prediction model as a performance prediction model; and a performance prediction model for predicting performance data of a target display device.

Patent Agency Ranking