Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Printing and typesetting system and method based on deep learning

A deep learning and printing technology, applied in special data processing applications, instruments, electrical digital data processing, etc., to achieve the effect of improving color separation and typesetting accuracy, improving production efficiency, and improving printing quality

Inactive Publication Date: 2018-08-21
广州多普网络科技有限公司 +1
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the technical problem of manual classification and typesetting according to the color of the document, to provide a kind of intelligent automatic printing and typesetting based on the color of the document that can simulate human senses, improve the printing work efficiency and printing quality, and print based on deep learning. Typesetting system and method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Printing and typesetting system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0041] A typesetting method for improving printing quality based on deep learning according to the present invention comprises the following steps:

[0042] S1. The printing and typesetting system acquires multiple pictures, collects feature information on the pictures, and generates a training set;

[0043] In the practical application of this embodiment, the characteristic information information of the picture includes the pattern on the picture, the pattern color system and the pattern layout; the fine picture collection box acquires the picture information of multiple pictures, and generates a training set through the training set module.

[0044] S2. The deep ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a printing and typesetting system and method based on deep learning. The method comprises the following steps that: a printing and typesetting system obtains a plurality of pictures, collects feature information on the pictures and generates a training set; the deep learning model of the printing and typesetting system trains the training set, and extracts the feature information of the pictures contained in the training of the deep learning model, and the printing and typesetting system analyzes the feature information so as to finish training the deep learning model;through the printing and typesetting system, the size of a printing layout is set; the printing and typesetting system obtains a picture to be printed and collects the feature information on the picture to be printed, and the deep learning model which finishes being trained in the S2 is combined with the printing layout of the S3 to carry out color classification on the picture to be printed and the arrangement of color distribution to generate a printing plate; and the printing and typesetting system outputs the printing plate to a printing unit, and the printing unit carries out production according to the printing layout.

Description

technical field [0001] The invention belongs to the technical field of printing automatic typesetting, and in particular relates to a printing typesetting system and method based on deep learning. Background technique [0002] Color printing is the reproduction of images or text in color. It involves many steps and conversion processes. Only through proper typesetting and distribution can high-quality color reproductions be produced. Due to the technical limitations of traditional printing machines and digital printing machines, in the printing process, in order to ensure the color quality of printed matter, if the same type of color on the printed matter is arranged in adjacent areas, the printing quality can be significantly improved. If the dark and light colors are arranged irregularly, or if the contrasting colors are arranged adjacent to each other, the output quality will be significantly reduced. At present, in the printing process such as business cards, leaflets, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/25G06K9/46G06F40/189
CPCG06F40/189G06V10/56
Inventor 杜俊荣
Owner 广州多普网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products