一种基于GA-BP神经网络结合PCA的LCD显示器光谱特征化模型

于海琦; 刘真; 田全慧

doi:10.3788/YJYXS20163102.0201

您当前的位置：

首页 >

文章列表页 >

一种基于GA-BP神经网络结合PCA的LCD显示器光谱特征化模型

显示与图像 | 更新时间：2020-08-12

- 一种基于GA-BP神经网络结合PCA的LCD显示器光谱特征化模型
- Spectral characterization model of liquid crystal display based on GA-BP neural network and PCA
- 液晶与显示 2016年31卷第2期页码：201-207
- 作者机构：
  
  1. 上海出版印刷高等专科学校上海,200093
  2. 上海理工大学出版印刷与艺术设计学院上海,200093
- 作者简介：
- 基金信息：
  
  国家自然科学基金-青年科学基金(No.61301231)()
- DOI：10.3788/YJYXS20163102.0201
  中图分类号： TP394.1;TH691.9
- 收稿日期：2015-03-28，
  
  修回日期：2015-06-05，
  
  纸质出版日期：2016-02-05
- 稿件说明：
移动端阅览
于海琦, 刘真, 田全慧. 一种基于GA-BP神经网络结合PCA的LCD显示器光谱特征化模型[J]. 液晶与显示, 2016,31(2): 201-207

YU Hai-qi, LIU Zhen, TIAN Quan-hui. Spectral characterization model of liquid crystal display based on GA-BP neural network and PCA[J]. , 2016,31(2): 201-207
于海琦, 刘真, 田全慧. 一种基于GA-BP神经网络结合PCA的LCD显示器光谱特征化模型[J]. 液晶与显示, 2016,31(2): 201-207 DOI： 10.3788/YJYXS20163102.0201.

YU Hai-qi, LIU Zhen, TIAN Quan-hui. Spectral characterization model of liquid crystal display based on GA-BP neural network and PCA[J]. , 2016,31(2): 201-207 DOI： 10.3788/YJYXS20163102.0201.

摘要

为实现 LCD显示器的光谱特征化

本文提出一种基于遗传算法优化(Genetic Algorithm

GA)的BP神经网络(GA-BP)结合PCA(Principal component analysis)的光谱特征化模型。首先对显示器色空间进行子空间划分

同时采用PCA对光谱数据进行降维

接着在各子空间中采用遗传算法对BP神经网络的权值阈值进行优化

建立显示器驱动值与光谱数据之间的神经网络模型

实现了显示器的光谱特征化。实验结果表明子空间划分后

在子空间中进行模型参数的优化有利于模型整体精度的提高

GA的优化有效改善了BP神经网络的极值问题

提高了模型的精度

PCA在不影响模型精度的同时提高了算法的运行效率。由此说明该模型是一种高精度显示器特征化模型。

Abstract

To achieve spectral characterization of LCD

a spectral characterization model based on GA-BP neural network and PCA was proposed in this paper. Firstly

color space of monitor was divided into subspaces and principal component analysis (PCA) was used to dimensionality reduction of the spectrum reflectance. Then genetic algorithm (GA) was adopted for optimizing the weight threshold of BP neural network in subspaces. A BP neural network was established to describe the transformation model of driver value and spectral reflectance. Lastly

the spectral characteristics model of LCD was realized. Experimental results show that model parameter optimization in the subspace is beneficial to the improvement of the model of overall after subspace division. The extremum problem of BP neural network can be improved by GA effectively.PCA can improve the operating efficiency of algorithm under the circumstances of maintaining accuracy. This implies that it is a high-precision display characteristic model.

关键词

Keywords

references

宫睿,徐海松,张显斗,等.液晶显示器色度特征化的分空间补偿模型[J].光学学报,2011,31(4):289-294. GONG R, XU H S, ZHANG X D, et al. Sub-space compensation model for accurate colorimetric characterization of liquid crystal displays[J]. Acta Optica Sinica, 2001, 31(4): 289-294. (in Chinese)

王勇,徐海松.液晶显示器颜色特征化的S模型算法[J].中国图象图形学报,2007,12(3):491-494. WANG Y, XU H S. The S shape model for LCD colorimetric characterization[J]. Journal of Image and Graphics, 2007, 12(3): 491-494. (in Chinese)

MICHAEL S, MATTHEW A, SRINIVASAN C, et al. A standard default color space for the internet-sRGB[EB/OL].(1996-11-05)http://www.w3.org/Graphics/Color/Srgb.html.

刘攀,刘真,朱明.基于最佳立方体细分的显示器颜色再现模型[J].包装工程,2014,35(13):128-132. LIU P, LIU Z, ZHU M. Monitor color reproduction model based on optimal cube subdivision[J]. Packaging Engineering, 2014, 35(13): 128-132. (in Chinese)

许宝卉,李言.基于ICC标准的CRT色空间转换方法的研究与比较[J].液晶与显示,2009,24(3):438-442. XU B H, LI Y. Research and comparison of CRT color space conversions based on ICC standard of color management[J]. Chinese Journal of Liquid Crystals and Displays, 2009, 24(3): 438-442. (in Chinese)

刘浩学,崔桂华,黄敏,等.按波长分区的LCD颜色特征化模型[J].光谱学与光谱分析,2013,33(10):2751-2757. LIU H X, CUI G H, HUANG M, et al. Colorimetric characterization of LCD based on wavelength partition spectral model[J]. Spectroscopy and Spectral Analysis, 2013, 33(10): 2751-2757. (in Chinese)

李金城.色彩高保真复制的理论与实践[D].南京:南京林业大学,2013. LI J C. Theory and practice of high-fidelity color reproduction[D]. Nanjing: Nanjing Forestry University, 2013. (in Chinese)

田亮,罗宇,王阳.基于遗传算法优化BP神经网络的TIG焊缝尺寸预测模型[J].上海交通大学学报,2013,47(11):1690-1696. TIAN L, LUO Y, WANG Y. Prediction model of TIG welding seam size based on BP neural network optimized by genetic algorithm[J]. Journal of Shanghai Jiaotong University, 2013, 47(11): 1690-1696. (in Chinese)

TZENG D Y, BERNS R S. A review of principal component analysis and its applications to color technology[J]. Color Research & Application, 2005, 30(2): 84-98.

FAIRMAN H S, BRILL M H. The principal components of reflectances[J]. Color Research & Application, 2004, 29(2): 104-110.

刘春艳,凌建春,寇林元,等.GA-BP神经网络与BP神经网络性能比较[J].中国卫生统计,2013,30(2):173-176. LIU C Y, LING J C, KOU L Y, et al. Performance comparison between GA-BP neural network and BP neural network[J].Chinese Journal of Health Statistics, 2013, 30(2): 173-176. (in Chinese)

罗戎蕾,刘绍华,苏晨.基于遗传算法的BP神经网络服装销售预测方法[J].北京邮电大学学报,2014,37(4):39-43. LUO R L, LIU S H, SU C. Garment sales forecast method based on genetic algorithm and BP neural network[J]. Journal of Beijing University of Posts and Telecommunications, 2014, 37(4): 39-43. (in Chinese)

余凡,赵英时,李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报,2012,31(3):283-288.

YU F, ZHAO Y S, LI H T. Soil moisture retrieval based on GA-BP neural networks algorithm[J]. Journal of Infrared and Millimeter Waves, 2012, 31(3): 283-288. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

显示驱动芯片原理及发展现状

某型液晶显示器夜间亮度变化不均匀现象的分析与改进

灰狼算法优化BP神经网络的图像去模糊复原

自适应多尺度颜色特征目标跟踪算法研究

一种多特征相结合的三维人脸关键点检测方法