Seven-color color separation model construction method based on polynomial regression algorithm

Abstract

The invention provides a seven-color color separation model construction method based on a polynomial regression algorithm, which is used in a multi-color color separation method and is characterized by comprising the following steps: 1, designing a test sample set, dividing cyan, magenta, yellow, black, red, green and blue into six groups according to hue angles, performing balanced sampling according to the dot area rate of each color to generate a test sample set, and printing and outputting the Lab color value of the test sample set through a multi-color printer; 2, taking the dot area rate of each color block in the test sample set as a dependent variable, taking the Lab color value of each color block as an independent variable, and establishing a polynomial regression model; 3, conducting parameter estimation on the polynomial regression model through a total least square method, obtaining all coefficients of the polynomial regression model, so that a seven-color color separation model based on CMYKRGB is established, wherein parameter estimation of the total least square method is shown in the specification.

Description

technical field [0001] The invention relates to a color separation method of a color image, in particular to a method for constructing a seven-color separation model based on a polynomial regression algorithm. Background technique [0002] With the increase of people's demand for high-end printing, the traditional CMYK 4-color printing is unable to accurately reproduce a large number of natural colors of the original due to the constraints of printing machinery and printing technology. Therefore, it is necessary to improve the existing traditional printing technology to meet this demand. On the basis of the traditional cyan (C), magenta (M), yellow (Y), and black (K) 4 primary colors, new primary colors are added for color reproduction, so as to achieve the purpose of expanding the color gamut, such as adding red (R), Three new primary colors of green (G) and blue (B) make the printing primary colors into 7 colors of CMYKRGB. The quality of the color separation model is the...

AI Technical Summary

Problems solved by technology

Among them, the y item is the dot area ratio of cyan (C), magenta (M), yellow (Y), black (K), red (R), green (G), and blue (B), and the X item represents the corresponding The Lab chromaticity value matrix, but the least squares method only considers the error of the y item, but the X item is also inaccurate in practical problems, because in the model construction, the color measuring instrument, air temperature, humidity, etc. will give The measurement of the Lab chromaticity value brings errors, so the input X in the polynomial regression equation is not accurate, so the parameter estimation method by the classical least square method will cause unsatisfactory training results

This not only fails to improve the accuracy of color reproduction, but also distorts the color of the image after reproduction, which runs counter to the original intention of high-fidelity multi-color reproduction

Images