Adaptation of one shot machine learning model trained on other registered images of other content for usage to instead identify whether input image includes content of registered images
US11630882B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 23, 2021 |
| Grant date | Apr 18, 2023 |
| Priority date | — |
| Expiry date | Jun 4, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V40/173
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Registered, first unregistered, and second unregistered encodings are generated for registered images of content, first unregistered images of the content, and second unregistered images of different content, respectively. First and second distance matrices having rows respectively corresponding to the first and second unregistered encodings are generated based on the registered encodings and the first and second unregistered encodings, respectively. A statistic is selected having a greatest difference between first and second distance vectors having values corresponding to the rows of the first and second distance matrices, respectively. Whether content of a new unregistered image corresponds to the content of the registered images is assessed by using the selected statistic.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.