Zero-shot sketch-based image retrieval techniques using neural networks for sketch-image recognition and retrieval
US10248664B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 2, 2018 |
| Grant date | Apr 2, 2019 |
| Priority date | — |
| Expiry date | Jul 2, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/32
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
This disclosure relates to improved sketch-based image retrieval (SBIR) techniques. The SBIR techniques utilize an architecture comprising three interconnected neural networks to enable zero-shot image recognition and retrieval based on free-hand sketches. Zero-shot learning may be implemented to retrieve one or more images corresponding to the sketches without prior training on all categories of the sketches. The neural network architecture may do so, at least in part, by training encoder hashing functions to mitigate heterogeneity of sketches and images, and by applying semantic knowledge that is learned during a limited training phase to unknown categories.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.