Synthesizing training data
US10049308B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 21, 2017 |
| Grant date | Aug 14, 2018 |
| Priority date | — |
| Expiry date | Feb 23, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30196
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Training images can be synthesized in order to obtain enough data to train a convolutional neural network to recognize various classes of a type of item. Images can be synthesized by blending images of items labeled using those classes into selected background images. Catalog images can represent items against a solid background, which can be identified using connected components or other such approaches. Removing the background using such approaches can result in edge artifacts proximate the item region. To improve the results, one or more operations are performed, such as a morphological erosion operation followed by an opening operation. The isolated item portion then can be blended into a randomly selected background region in order to generate a synthesized training image. The training images can be used with real world images to train the neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.