Object color management using raster image processors and object detection and semantic segmentation
US12034903B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 27, 2023 |
| Grant date | Jul 9, 2024 |
| Priority date | — |
| Expiry date | Oct 27, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A raster image processor and a convolutional neural network or other artificial intelligence module operate in parallel. Image data for printing is passed to the raster image processor and the convolutional neural network. The raster image processor translates computer vector files and/or rasterizes bitmaps having higher or lower resolution than the output device to a raster image that includes a matrix of dots a printer can process. The raster image processor generates layers for process inks. The convolutional neural network generates a mask layer, based on the image, that is used by the raster image processor to generate an additional layer for spot colors, object colors, or specialty ink. The mask layer transmitted to the raster image processor generates a spot color layer. The layers generated by the raster image processor and the additional layer for the spot colors and/or specialty inks are combined into a print data file.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.