计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (13): 164-167.DOI: 10.3778/j.issn.1002-8331.2010.13.049

• 图形、图像、模式识别 • 上一篇    下一篇

基于自适应局部非线性回归的颜色校正算法

马玫娟1,2,蔡轶珩1,2,张新峰1,徐晓昭1   

  1. 1.北京工业大学 信号与信息处理研究室,北京 100124
    2.北京工业大学 机械工程与应用电子技术学院,北京 100124
  • 收稿日期:2008-10-22 修回日期:2009-05-04 出版日期:2010-05-01 发布日期:2010-05-01
  • 通讯作者: 马玫娟

Color correction method based on self-adaptive local nonlinear regression

MA Mei-juan1,2,CAI Yi-heng1,2,ZHANG Xin-feng1,XU Xiao-zhao1   

  1. 1.Signal & Information Processing Lab,Beijing University of Technology,Beijing 100124,China
    2.College of Mechanical Engineering and Applied Electronics,Beijing University of Technology,Beijing 100124,China
  • Received:2008-10-22 Revised:2009-05-04 Online:2010-05-01 Published:2010-05-01
  • Contact: MA Mei-juan

摘要: 颜色是图像的重要信息。许多颜色校正算法都采用精度较高的查找表法。为了更好地拟合颜色空间之间复杂的映射关系,在自适应局部线性回归颜色校正模型的基础上提出了基于自适应局部非线性回归的颜色校正模型,在小样本情况下,自适应地选择插值点的个数,利用局部非线性回归模型优化权值,建立三维的查找表,实现较好的颜色校正效果。实验证明基于自适应局部非线性回归的颜色校正模型的校正精度整体高于基于自适应局部线性回归的颜色校正模型的校正精度。

关键词: 局部非线性回归, 查找表, 颜色校正

Abstract: Color is important information of an image.Several color correction methods are used to establish Look-up table,which is one of popular ways for color reproduction,so that high accuracy can be achieved.A color correction method based on self-adaptive local nonlinear regression is presented,for nonlinear regression can better fit the complex mapping of color spaces.Under small sampling condition,the color correction method adaptively selects the most optimized neighborhood size and applies local nonlinear regression to optimize the weights,then establishes 3D Look-up table so that ideal performance can be achieved.The results of experiment show that the accuracy of color correction method based on self-adaptive local nonlinear regression is higher than that of the color correction model based on self-adaptive local linear regression.

Key words: local nonlinear regression, look-up table, color correction

中图分类号: