基于子空间划分的多项式回归多色分色算法  

Polynomial Regression Multi-color Separation Method Based on Subspace Partition

作　　者：张桢杰[1] 刘真[1] 吴明光[2] 

机构地区：[1]上海理工大学,上海200093 [2]南京师范大学虚拟地理环境教育部重点实验室,南京200046

出　　处：《包装工程》2013年第7期65-67,76,共4页Packaging Engineering

基　　金：国家自然科学基金资助项目(41271446)

摘　　要：提出了一种新的分色算法。方法首先对多色打印机进行色域分区,再将每个分区划分成若干个子空间,在每个子空间内运用最小二乘法建立多项式模型,对目标色度值进行分色时,搜索目标色度值所在最优子空间,求解对应的多项式方程,即可得到分色结果。实验表明,这种分色算法具有较高的精度和稳定性,能够满足多色高精度印刷的要求。A new color separation method was proposed. Multi-color printer gamut was separated into partitions ; every partition was divided into subspaces. Polynomial models were created in subspaces with least square method. Optimal subspace was found first when the targeting colorimetric value was in color separation. Separation resuh was obtained by solving polynomial equation. The experiment showed that this separation method performs well in accuracy and stability and satisfies the requirement of muhi-eolor high-precision printing.

关 键 词：多色分色 多项式回归 子空间 分区 

分 类 号：TS801.3[轻工技术与工程] TS807