SYSTEMS AND METHODS FOR AUTOMATIC QUALITY CONTROL OF IMAGE RECONSTRUCTION

    公开(公告)号:EP4446994A1

    公开(公告)日:2024-10-16

    申请号:EP24163173.8

    申请日:2024-03-13

    发明人: CARMI, Raz

    IPC分类号: G06T11/00

    摘要: Various methods and systems are provided for automatic quality control of image reconstruction. In one example, a method comprises obtaining medical image data (302), reconstructing the medical image data with a baseline reconstruction algorithm to generate one or more baseline reconstruction images (304) and an enhanced reconstruction algorithm to generate one or more enhanced reconstruction images (306), detecting (308) and localizing (310) a set of features of interest within the one or more baseline reconstruction images, determining image values for each of the features of interest (312), comparing image values of the one or more baseline reconstruction images to corresponding image values of the one or more enhanced reconstruction images to determine one or more statistical characteristics (314), comparing the one or more statistical characteristics to predetermined criteria to determine deviations (316), and automatically modifying one or more parameters of the enhanced reconstruction algorithm based on the deviations (322).

    VIDEO GENERATION METHOD AND DEVICE
    7.
    发明公开

    公开(公告)号:EP4435724A2

    公开(公告)日:2024-09-25

    申请号:EP22912123.1

    申请日:2022-12-22

    申请人: Lemon Inc.

    摘要: Provided in the embodiments of the present disclosure are a video generation method and device. The method comprises: extracting a first image feature from a first image; according to the first image feature and a second image feature, obtaining a plurality of intermediate image features by means of nonlinear interpolation, wherein the second image feature is an image feature of a second image; and performing image reconstruction by means of an image generation model and on the basis of the first image feature, the second image feature and the plurality of intermediate image features, so as to generate a target video, wherein the target video is used for presenting a process of a gradual change from the first image to the second image. Therefore, the quality of intermediate image features is improved by means of nonlinear interpolation, and thus the image quality of intermediate frames of a target video is improved, that is, the video quality of the target video is improved.

    DEFECT DETECTION USING SYNTHETIC DATA AND MACHINE LEARNING

    公开(公告)号:EP4375939A3

    公开(公告)日:2024-08-21

    申请号:EP24170589.6

    申请日:2022-10-18

    IPC分类号: G06T7/00 G06T11/00

    摘要: A method for quality control of contact lens packages comprises receiving a first data set comprising a plurality of images of a contact lens package having physically implanted defects; receiving a second data set comprising a plurality of images of a contact lens package having digitally implanted defects; testing and training, on the first and second data set, a model to determine a validated one or more quality control models; capturing image data of a package of a contact lens; analyzing, based on the validated one or more quality control models, the image data; and causing, based on the analyzing, output of a quality control metric indicative of at least an accept or reject condition of the package.