首页 | 官方网站   微博 | 高级检索  
     

A Four-color Matching Method Combining Neural Networks with Genetic Algorithm
引用本文:苏小红,Wang Yadong,ZHANG Tianwen. A Four-color Matching Method Combining Neural Networks with Genetic Algorithm[J]. 高技术通讯(英文版), 2003, 9(4): 39-43
作者姓名:苏小红  Wang Yadong  ZHANG Tianwen
作者单位:SchoolofComputerScienceandTechnology,HarbinInstituteofTechnology,Harbin150001,P.R.China
基金项目:SupportedbytheNationalNaturalScienceFoundationofChina
摘    要:A brief review of color-matching technology and its application of printing RGB images by CMY or CMYK ink-jet printers is presented, followed by an explanation to the conventional approaches that are commonly used in color-matching. Then, a four-color matching method combining neural network with genetic algorithm is proposed. The initial weights and thresholds of the BP neural network for RGB-to-CMY color conversion are optimized by the new genetic algorithm based on evolutionarily stable strategy. The fourth component K is generated by using GCR (Gray Component Replacement) concept. Simulation experiments show that it is well behaved in both accuracy and generalization performance.

关 键 词:神经网络 遗传算法 四色匹配法 喷墨打印机

A Four-color Matching Method Combining Neural Networks with Genetic Algorithm
Wang Yadong,ZHANG Tianwen. A Four-color Matching Method Combining Neural Networks with Genetic Algorithm[J]. High Technology Letters, 2003, 9(4): 39-43
Authors:Wang Yadong  ZHANG Tianwen
Abstract:A brief review of color matching technology and its application of printing RGB images by CMY or CMYK ink jet printers is presented, followed by an explanation to the conventional approaches that are commonly used in color matching. Then, a four color matching method combining neural network with genetic algorithm is proposed. The initial weights and thresholds of the BP neural network for RGB to CMY color conversion are optimized by the new genetic algorithm based on evolutionarily stable strategy. The fourth component K is generated by using GCR (Gray Component Replacement) concept. Simulation experiments show that it is well behaved in both accuracy and generalization performance.
Keywords:color matching   color reproduction   back propagation (BP) neural networks   genetic algorithm
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号