Machine-Learned Color Profile Estimation for Ink Limit Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for creating color conversion profiles in printing apparatuses require extensive man-hours and repeated printing and imaging to set appropriate limit values for ink discharge, leading to inefficiencies and potential issues like ink overflowing, bleeding, or aggregation.
Innovation Solution
An information processing apparatus that utilizes a machine-learned model to estimate the maximum or minimum amount of ink per unit area based on the type of printing medium and imaging information, allowing for the creation of a color conversion profile that maps coordinate values in a color space to ink amounts, thereby reducing the need for repeated printing and imaging.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If repeated printing and imaging is performed to determine upper limit values for each effect, then the accuracy of color conversion profile is improved, but the time required for profile creation increases significantly
Solution Approach 1:
The system performs preliminary printing of a test pattern and imaging to acquire imaging information before actual color conversion profile creation. This preliminary action allows the machine learning model to be trained in advance, so that when creating the color conversion profile, the system can quickly estimate upper limit values without needing to perform repeated printing and imaging for each effect, thus resolving the contradiction between accuracy and time consumption
Solution Approach 2:
The system uses imaging information (a copy or representation of the printed test pattern) to train a machine learning model that can predict upper limit values. Instead of performing physical printing and imaging repeatedly, the system creates a digital model that replicates the behavior of the printing system, allowing rapid estimation of parameters without physical iteration, thereby reducing time while maintaining accuracy
2Manufacturing precision
If manual determination of upper limit values is performed for each effect, then the quality of printing is improved, but the complexity of the process increases
Solution Approach 1:
The system enables the printing apparatus to automatically determine upper limit values for coloring materials by using its own imaging information and a trained machine learning model. The apparatus performs self-diagnosis and self-adjustment without requiring external manual intervention for each effect, thereby maintaining high printing quality while reducing process complexity and making the system more autonomous
Solution Approach 2:
The system changes the approach from manual parameter determination to automated parameter estimation using machine learning. By transforming the upper limit values into estimable parameters based on imaging information and medium type, the system simplifies the creation process while maintaining the quality benefits of precise parameter control, resolving the contradiction between quality and complexity
Data Source
AI summary
An information processing apparatus configured to store a machine-learned model that learned, by machine learning, a relationship between a type of a printing medium, an amount of a coloring material on the printing medium per unit area, and an image including a linear image and printed on the printing medium; and estimate, based on a selection information and a imaging information, by using the machine-learned model, a limit value indicating a maximum value or a minimum value of an amount of the coloring material to be used for printing on the printing medium by the printing section per unit area; and create, by using the limit value, a color conversion profile including information regarding mapping between a coordinate value in a color space and an amount of the coloring material.