Deep learning based on image encoding and decoding
US11593632B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 22, 2017 |
| Grant date | Feb 28, 2023 |
| Priority date | — |
| Expiry date | May 31, 2039 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N19/91
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A deep learning based compression (DLBC) system trains multiple models that, when deployed, generates a compressed binary encoding of an input image that achieves a reconstruction quality and a target compression ratio. The applied models effectively identifies structures of an input image, quantizes the input image to a target bit precision, and compresses the binary code of the input image via adaptive arithmetic coding to a target codelength. During training, the DLBC system reconstructs the input image from the compressed binary encoding and determines the loss in quality from the encoding process. Thus, the models can be continually trained to, when applied to an input image, minimize the loss in reconstruction quality that arises due to the encoding process while also achieving the target compression ratio.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.