公开(公告)号：US11798263B1

公开(公告)日：2023-10-24

申请号：US18295337

申请日：2023-04-04

Applicant: SAS Institute Inc.

Inventor： Kedar Shriram Prabhudesai ,  Jonathan Lee Walker ,  Sanjeev Shyam Heda ,  Varunraj Valsaraj ,  Allen Joseph Langlois ,  Frederic Combaneyre ,  Hamza Mustafa Ghadyali ,  Nabaruna Karmakar

IPC: G06V10/764 ,  G06V10/24 ,  G06V10/82 ,  G06T7/00 ,  G06V10/26

CPC classification number: G06V10/764 ,  G06T7/0006 ,  G06V10/24 ,  G06V10/273 ,  G06V10/82 ,  G06T2207/30164

Abstract: A computing system detects a defective object. An image is received of a manufacturing line that includes objects in a process of being manufactured. Each pixel included in the image is classified as a background pixel class, a non-defective object class, or a defective object class using a trained neural network model. The pixels included in the image that were classified as the non-defective object class or the defective object class are grouped into polygons. Each polygon is defined by a contiguous group of pixels classified as the non-defective object class or the defective object class. Each polygon is classified in the non-defective object class or in the defective object class based on a number of pixels included in a respective polygon that are classified in the non-defective object class relative to a number of pixels included in the respective polygon that are classified in the defective object class.