一种基于LASSO回归模型的彩色相机颜色校正方法

doi:10.7517/j.issn.1674-0475.2017.02.153

影像科学与光化学 ›› 2017, Vol. 35 ›› Issue (2): 153-161.DOI: 10.7517/j.issn.1674-0475.2017.02.153

一种基于LASSO回归模型的彩色相机颜色校正方法

郭越¹, 高昆¹, 朱钧², 豆泽阳¹, 黄亚东¹, 冯云鹏³

1. 北京理工大学光电成像技术与系统教育部重点实验室, 北京 100081;
2. 清华大学精密仪器与机械学系, 北京 100084;
3. 北京理工大学深圳研究院, 广东深圳 518057

收稿日期:2017-01-23 修回日期:2017-02-16 出版日期:2017-03-15 发布日期:2017-03-15
通讯作者: 高昆
基金资助:
北京自然科学基金项目（4152045）资助

A Color Correction Method of Color Camera Based on LASSO Regression Model

GUO Yue¹, GAO Kun¹, ZHU Jun², DOU Zeyang¹, HUANG Yadong¹, FENG Yunpeng³

1. Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education, Beijing Institute of Technology, Beijing 100081, P. R. China;
2. Department of Precision Instrument, Tsinghua University, Beijing 100084, P. R. China;
3. Shenzhen Research Institute, Beijing Institute of Technology, Shenzhen 518057, Guangdong, P. R. China

Received:2017-01-23 Revised:2017-02-16 Online:2017-03-15 Published:2017-03-15

摘要/Abstract

摘要：

彩色相机的颜色校正是实现成像色彩一致性的必要保障手段。传统的相机颜色校正中，对测量数据多采用多项式回归分析来确定颜色定标系数，存在着精度不高的缺点，因此，本文对测量数据提出了基于LASSO的高阶多项式回归拟合方法，利用LASSO压缩系数的特点，在保证计算复杂度的前提下，有效提高了回归模型的校正精度。在D65标准光源下对ColorChecker 24色卡进行了实际成像实验，并用CIELAB色差公式表征了校正效果，实验结果表明，新方法的校正效果明显优于传统的线性回归、二次多项式回归方法，平均色差指标可以达到5个CIELAB色差单位。

关键词: 颜色校正, LASSO回归, 多项式回归

Abstract:

Color correction is the essential safeguard method to keep the image color constancy for a color camera. In traditional color correction methods, the color calibration coefficients are mostly obtained by the polynomial regression model, whose correction accuracy is often insufficient. So a high order polynomial fitting method based on LASSO (Least Absolute Shrinkage and Selection Operator) regression model is proposed, considering that LASSO can compress the polynomial coefficients efficiently to guarantee the model complexity and improve the correction precision as well. The experiments are conducted using D65 standard light source and ColorChecker 24 as the imaging object. The results characterized by CIELAB color difference function show that compared with traditional linear regression and quadratic polynomial regression methods, the images corrected by LASSO method has a better effect, with the mean color difference value about 5.

Key words: color correction, LASSO regression, polynomial regression

郭越, 高昆, 朱钧, 豆泽阳, 黄亚东, 冯云鹏. 一种基于LASSO回归模型的彩色相机颜色校正方法[J]. 影像科学与光化学, 2017, 35(2): 153-161.

GUO Yue, GAO Kun, ZHU Jun, DOU Zeyang, HUANG Yadong, FENG Yunpeng. A Color Correction Method of Color Camera Based on LASSO Regression Model[J]. Imaging Science and Photochemistry, 2017, 35(2): 153-161.

参考文献

[1] Lam E Y, Fung G S K. Single-Sensor Imaging:Methods and Applications for Digital Cameras[M]. Boca Raton:CRC Press, 2008. 267-294.
[2] 董俊鹏. 基于光照分析的颜色恒常性算法研究[D].合肥工业大学, 2015. Dong J P. Research of color constancy algorithm based on illumination analysis[D]. Hefei University of Technology, 2015.
[3] 徐晓昭, 沈兰荪, 刘长江. 颜色校正方法及其在图像处理中的应用[J]. 计算机应用研究, 2008, 25(8):2250-2254. Xu X Z, Shen L S, Liu C J. Color correction methods and application in image processing[J]. Application Research of Computers, 2008, 25(8):2250-2254.
[4] 宫睿.智能移动终端图像显示性能评价方法及应用研究[D]. 浙江大学, 2014. Gong R. Study of assessment method and application for image display performance of smart mobile devices[D]. Zhejiang University, 2014.
[5] 丁二锐, 王义峰, 曾平, 丁阳. 基于结构风险最小化和全最小二乘法的色彩校正[J]. 电子与信息学报, 2008, 30(3):717-720. Ding E R, Wang Y F, Zeng P, Ding Y. Color calibration based on structural risk minimizationand total least squares[J]. Journal of Electronics & Information Technology, 2008, 30(3):717-720.
[6] 刘关松, 吕嘉雯, 徐建国, 高敦岳. 监督颜色校正方法研究[J]. 计算机学报, 2003, 26(4):502-506. Liu G S, Lv J W, Xu J G, Gao D Y. The study of supervised color correction[J]. Chinese Journal of Computers, 2003, 26(4):502-506.
[7] Kim S J, Koh K M, Lustig M, Boyd S, Gorinevsky D. An interior-point method for large-scale-regularized least squares[J]. IEEE Journal of Selected Topics in Signal Processing, 2007, 1(4):606-617.
[8] Xu Z B, Zhang H, Wang Y, Chang X Y, Liang Y. L1/2 regularization[J]. Science China Information Sciences, 2010, 53(6):1159-1169.
[9] Tibshirani R. Regression shrinkage and selection via the lasso:a retrospective[J]. Journal of the Royal Statistical Society:Series B (Statistical Methodology), 2011, 73(3):273-282.
[10] 张靖. 面向高维小样本数据的分类特征选择算法研究[D]. 合肥工业大学, 2014. Zhang J. Classification and feature selection on high-dimensional and small-sampling data[D]. Hefei University of Technology, 2014.
[11] Bradley E, Trevor H, Iain J, Tibshirani R. Least angle regression[J]. The Annals of Statistics, 2004, 32(2):407-499.
[12] 柯郑林. Lasso及其相关方法在多元线性回归模型中的应用[D]. 北京交通大学, 2011. Ke Z L. The application of Lasso and its related methods in multiple linear regression model[D]. Beijing Jiaotong University, 2011.
[13] 刘柳, 陶大程. Lasso问题的最新算法研究[J]. 数据采集与处理, 2015, 30(1):35-46. Liu L, Tao D C. Review on recent method of solving Lasso problem[J]. Journal of Data Acquisition and Processing, 2015, 30(1):35-46.
[14] 方竞宇, 徐海松, 汪哲弘, 吴晓玟. 相机参数可变的齐次多项式色度特征化模型[J]. 光学学报, 2016, 36(8):309-316. Fang J Y, Xu H S, Wang Z H, Wu X W. Homogeneous polynomial model for colorimetric characterization of camera with variable settings[J]. Acta Optica Sinica, 2016, 36(8):309-316.

一种基于LASSO回归模型的彩色相机颜色校正方法

A Color Correction Method of Color Camera Based on LASSO Regression Model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价