公开(公告)号：US20250054293A1

公开(公告)日：2025-02-13

申请号：US18718680

申请日：2022-11-29

Applicant: MEC COMPANY LTD.

Inventor： Masako AKAGI

IPC: G06V10/98 ,  G06T7/00 ,  G06V10/77 ,  G06V10/82

Abstract: The physical property value prediction method include: inputting a plurality of prediction target images for each of which a measured value of the physical property value is known into a machine-learned prediction model, and outputting a predicted value and a feature map of each of the plurality of prediction target images; identifying, on a basis of prediction results from images almost identical in measured physical property value among the plurality of prediction target images, a poor prediction image and a good prediction image; and extracting a feature group representing a factor in poor prediction on a basis of a difference between a frequency distribution of a plurality of features constituting the feature map of the poor prediction image and a frequency distribution of a plurality of features constituting the feature map of the good prediction image.

公开(公告)号：US20250069371A1

公开(公告)日：2025-02-27

申请号：US18722545

申请日：2022-11-29

Applicant: MEC COMPANY LTD.

Inventor： Masako AKAGI ,  Tristan HASCOET ,  Xuejiao DENG

IPC: G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V20/69

Abstract: The physical property value prediction method include: acquiring a prediction target image of a prediction target material; inputting the prediction target image into a prediction model machine-learned so as to receive an input of the image of the material as an explanatory variable and output the physical property value of the material, and outputting the physical property value of the material appearing in the prediction target image as a predicted value.