Geometrically constrained, unsupervised training of convolutional autoencoders for extraction of eye landmarks
US11514720B2 · kind B2 · utility
8Cited by
0References
11Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 2, 2020 |
| Grant date | Nov 29, 2022 |
| Priority date | — |
| Expiry date | Jan 2, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20132
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The disclosure relates to systems, methods and programs for geometrically constrained, unsupervised training of convolutional autoencoders on unlabeled images for extracting eye landmarks. Disclosed systems for unsupervised deep learning of gaze estimation in eyes' image data are implementable in a computerized system. Disclosed methods include capturing an unlabeled image comprising the eye region of a user; and training a plurality of convolutional autoencoders on the unlabeled image comprising the eye region of a user using an initial geometrically regularized loss function to determine a plurality of eye landmarks.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.