System and method for classification and authentication of identification documents using a machine learning based convolutional neural network
US10217179B2 · kind B2 · utility
5Cited by
0References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Oct 17, 2017 |
| Grant date | Feb 26, 2019 |
| Priority date | — |
| Expiry date | Oct 17, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/95
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure describes systems and methods to classify and authenticate ID documents based on the information contained on the face of the ID document. This present system can automatically classify, authenticate, and extracting data from documents using artificial intelligence (AI) based machine learning for image recognition. In some implementations, the machine learning techniques include a convolutional neural network. The system can also determine the authenticity of other documents, such as currency, stamps, and invoices.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.