基于GRNN神经网络的颜色空间转换研究

Research on Color Space Conversion Based on GRNN Neural Network

印刷的原理就是从标准色空间到印刷色空间的一种非线性转换,纽介堡方程是连接这两个空间的纽带。首先设计好印刷测试样张,测量各专色的XYZ值和网点面积率值,将实测值和计算值进行比较,分析误差的范围。利用实验所得数据对纽介堡方程进行仿真,结果表明:GRNN法较传统的高斯-赛德尔法有效。

The principle of printing is a nonlinear conversion from standard color space to printing color space. Neugebauer equation is a bond between the two color spaces. The printing sample testing pages should be designed first, the XYZ value and area ration of note in every spot-color area are measured, and then, the error of the data is analyzed by comparing the measured value with the cal- culated value. The data which has been acquired in experiment are used to simulate the Neugebauer equation, and the findings show that the way by using GRNN is more effective to that by using Gauss-Seidel iterative method.