Systems and methods for hierarchical webly supervised training for recognizing emotions in images
US10915798B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | May 15, 2018 |
| Grant date | Feb 9, 2021 |
| Priority date | — |
| Expiry date | Nov 8, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V2201/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed herein are embodiments of systems, methods, and products for a webly supervised training of a convolutional neural network (CNN) to predict emotion in images. A computer may query one or more image repositories using search keywords generated based on the tertiary emotion classes of Parrott's emotion wheel. The computer may filter images received in response to the query to generate a weakly labeled training dataset labels associated with the images that are noisy or wrong may be cleaned prior to training of the CNN. The computer may iteratively train the CNN leveraging the hierarchy of emotion classes by increasing the complexity of the labels (tags) for each iteration. Such curriculum guided training may generate a trained CNN that is more accurate than the conventionally trained neural networks.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.