Computer-implemented system for image quality enhancement and color spaces convertion for manufactured surfaces printers

A computer-implemented system for image quality enhancement and color spaces conversion for images to be printed on manufactured surfaces, wherein the process implemented by the computer implemented system 1 is as follows:

• (
• g
• ∘
• f
• )
• ⁢
• (
• x
• ′
• )
• =
• g
• ⁡
• (
• f
• ⁡
• (
• x
• ′
• )
• )
• =
• g
• ⁡
• (
• x
• ″
• )
• =
• x
• +
• ″
• where:
• x′ is the original image in RGB space;
• x″ is the converted image in multichannel space;
• x+″ is the enhanced image in multichannel space that can be used in manufactured surfaces printers;
• ƒ is the conversion function ƒ(x′)=x″;
• g is the enhancement function g(x″)=x+″ that represents the enhancement work carried out by a graphic designer on the converted image x″ in the multichannel space for obtaining an enhanced image x+″ in multichannel space for the use with said manufactured surfaces printers, wherein
• the computer-implemented system comprising at least a convolutional neural network trained by means of a training dataset with images divided in three groups:
• initial RGB images that have to be enhanced with a specific color profile multichannel space that can be used in said manufactured surfaces printers,
• converted images starting from each of said RGB images, by applying said color profile;
• and
• for each of the RGB images, an enhanced version of said converted images by applying said color profile, wherein
• said convolutional neural network configured for executing at least the following steps:
• receive in input an original image x′ in RGB space;
• from the original image x′, generate an approximation {tilde over (x)}+″ of an enhanced image x+″ in said specific color profile multichannel space for said manufactured surfaces printers;
• and
• return to output said approximation {tilde over (x)}+″ of the enhanced image x+″ for the use in said manufactured surfaces printers.