公开(公告)号：US20240095911A1

公开(公告)日：2024-03-21

申请号：US18284484

申请日：2022-03-31

Applicant: BASF SE

Inventor： Rahul TANEJA ,  Kamran SIAL ,  Till EGGERS ,  Margret KEUPER ,  Ramon NAVARRA-MESTRE ,  Sebastian FISCHER ,  Mike SCHARNER ,  Javier ROMERO RODRIGUEZ ,  Francisco Manuel POLO LOPEZ ,  Andres MARTIN PALMA

IPC: G06T7/00 ,  A01G7/00 ,  G06T7/62 ,  G06V10/764 ,  G06V20/10

CPC classification number: G06T7/0012 ,  A01G7/00 ,  G06T7/0004 ,  G06T7/62 ,  G06V10/764 ,  G06V20/188 ,  G06T2200/24 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06T2207/30188

Abstract: The present disclosure relates to image processing or computer vision techniques. A computer-implemented method is provided for determining a damage status of a physical object, the method comprising the steps of receiving a surface image of the physical object; and providing a pre-trained machine learning model to derive property values from the received surface map, wherein each property value is indicative of a damage index at a respective location, wherein the property values are preferably usable for monitoring and/or controlling a production process of the physical object. In this way, it is possible to reliably identify local defects and ensure that it is accurate enough to apply the chemical products in suitable amounts.