System and method for synthetic image training of a neural network associated with a casino table game monitoring system
US11205319B2 · kind B2 · utility
0Cited by
80References
18Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | May 27, 2020 |
| Grant date | Dec 21, 2021 |
| Priority date | — |
| Expiry date | Jun 12, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG07F17/3223
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed are a system and method for training a neural network associated with a casino table game monitoring system. Synthetic images of objects extracted from a virtual table game environment are used to create a ground truth set, which is then used to train and test a neural network. When the neural network's classification of the extracted images is deemed accurate enough, the neural network may then be deployed in a casino to track the use of corresponding physical objects in real casino table game play as part of the casino table game monitoring system.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.