Technique for machine visual learning
US11397872B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 6, 2018 |
| Grant date | Jul 26, 2022 |
| Priority date | — |
| Expiry date | Apr 11, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20081
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of expanding a visual learning database in a computer by teaching the computer includes providing a series of training images to the computer wherein each series includes three images with each image falling within a unique image domain and with each image domain representing a possible combination of a first attribute and a second attribute with a first image domain including the first attribute and the second attribute in a first state (X=0, Y=0), a second image domain including the first attribute in a second state and the second attribute in the first state (X=1, Y=0), and a third image domain including the first attribute in the first state and the second attribute in the second state (X=0, Y=1). The method also includes developing within the computer forward generators and reverse generators between the first image domain, the second image domain, the third image domain, and a fourth image domain for which no training image is provided, and applying with the computer the forward generators and reverse generators to single images that fall within one of the first image domain, the second image domain, the third image domain, and a fourth image domain to generate image…
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.