Complex color space conversion using convolutional neural networks
US12132879B1 · kind B1 · utility
0Cited by
2References
14Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 18, 2023 |
| Grant date | Oct 29, 2024 |
| Priority date | — |
| Expiry date | Sep 18, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/08
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A device such as a color printer includes a main memory, a cache memory, and a convolutional neural network configured to convert pixels from a first color space to a second color space. The convolutional neural network is organized into execution-separable layers, and loaded one or more layer at a time (depending on cache size) from the main memory to the cache memory, whereby the pixels are processed through each of the layers in the cache memory, and layers that have completed processing are evicted to make room for caching next layer(s) of the network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.