Hierarchical constrained automatic learning network for character recognition
US5058179A · kind A · utility
37Cited by
6References
14Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 31, 1990 |
| Grant date | Oct 15, 1991 |
| Priority date | — |
| Expiry date | Jan 31, 2010 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Highly accurate, reliable optical character recognition is afforded by a hierarchically layered network having several layers of parallel constrained feature detection for localized feature extraction followed by several fully connected layers for dimensionality reduction. Character classification is also performed in the ultimate fully connected layer. Each layer of parallel constrained feature detection comprises a plurality of constrained feature maps and a corresponding plurality of kernels wherein a predetermined kernel is directly related to a single constrained feature map. Undersampling is performed from layer to layer.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.