Patent · US Active

Method for neural network training using differences between a plurality of images, and apparatus using the method

US10643107B1 · kind B1 · utility

4Cited by
0References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 13, 2019
Grant dateMay 5, 2020
Priority date
Expiry dateNov 13, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V2201/03
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present disclosure provides a method for training a neural network that extracts a feature of an image by using data related to a difference between image, and an apparatus using the same. A neural network training method performed by a computing device according to an exemplary embodiment of the present disclosure includes: acquiring a reference image photographed with a first setting with respect to an object and a first comparison image photographed with a second setting with respect to the object; acquiring feature data of the reference image from a first neural network trained by using the reference image; acquiring feature data of a first extract image from a second neural network, wherein the second neural network is trained by using the first extract image formed from data related to a difference between the reference image and the first comparison image; and training a third neural network by using the feature data of the reference image and the feature data of the first extracted image.

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