Patent · US Active

Method for detecting anomaly using generative adversarial networks, apparatus and system thereof

US10733733B1 · kind B1 · utility

7Cited by
0References
20Claims
0Family size

Assignee

Inventor

Key dates

Filing dateAug 8, 2019
Grant dateAug 4, 2020
Priority date
Expiry dateAug 8, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/30096
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

There is provided an anomaly detection method, apparatus, and system that can improve the accuracy and reliability of a detection result using GAN (Generative Adversarial Networks). An anomaly detection apparatus according to some embodiments includes a memory that stores a GAN-based image translation model and an anomaly detection model, and a processor that translates a learning image with a low-difficulty level into a learning image with a high-difficulty level and learns the anomaly detection model using the translated learning image. The anomaly detection apparatus can improve the detection performance by learning the anomaly detection model with the learning image with the high-difficulty level in which it is difficult detect the anomaly.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.