互补色小波颜色恒常性/白平衡方法

陈扬; 李旦; 张建秋

doi:10.16383/j.aas.c180037

互补色小波颜色恒常性/白平衡方法

doi: 10.16383/j.aas.c180037

陈扬^1,,
李旦^1, ,,
张建秋^1,

1.
复旦大学信息科学与工程学院智慧网络与系统研究中心和电子工程

基金项目:

国家自然科学基金 61571131

详细信息

作者简介:
陈扬复旦大学电子工程系博士研究生.主要研究方向为图像/视频处理. E-mail: 13110720040@fudan.edu.cn

张建秋复旦大学电子工程系教授.主要研究方向为信号处理及其在通信、控制、测量、图像和雷达中的应用. E-mail: jqzhang@ieee.org

通讯作者:
李旦复旦大学电子工程系讲师.主要研究方向为数字信号处理及应用.本文通信作者. E-mail: lidan@fudan.edu.cn

计量
- 文章访问数: 1293
- HTML全文浏览量: 66
- PDF下载量: 109
- 被引次数: 0
出版历程
- 收稿日期: 2018-01-17
- 录用日期: 2018-08-14
- 刊出日期: 2020-07-24

Color Constancy With Complementary Color Wavelets

CHEN Yang^1
,,
LI Dan^{1
, ,},
ZHANG Jian-Qiu^1
,

1.
Department of Electronic Engineering and the Research Center of Smart Networks and Systems, School of Information Science and Technology, Fudan University, Shanghai 200433

Funds:

National Natural Science Foundation of China 61571131

More Information

Author Bio:
CHEN Yang Ph. D. candidate in the Department of Electronic Engineering, Fudan University. His research interest covers the multiresolution filtering and image/video processing

ZHANG Jian-Qiu Professor in the Department of Electronic Engineering, Fudan University. His research interest covers signal processing and its application

Corresponding author: LI Dan Lecturer in Department of Electronic Engineering, Fudan University. His research interest covers digital signal processing and its application to nondestructive testing. Corresponding author of this paper

摘要

摘要: 借助于互补色小波, 本文提出一种新的颜色恒常性统计方法.分析表明:标准光照图像的互补色小波子带关系, 可以利用联合拉普拉斯分布来进行描述.统计学习标准光照图像, 可获得拉普拉斯分布的参数, 为图像建立起标准光照的基准模型.该基准模型可为光照偏移(颜色恒常偏移)的图像提供光照补偿依据, 使偏光图像通过光照补偿恢复为标准光照图像, 从而得到光照参数.基于该基准模型对补偿光照参数进行最大似然估计的实验结果表明:本文所提方法的处理效果与列出的最好文献算法相当, 其在常用数据库上估计到的光照参数误差中值小0.1°, 而均值和最大值则小0.3°.
- 色恒常性 /
- 白平衡 /
- 互补色小波 /
- 彩色图像
Abstract: By means of the recent reported complementary color wavelet transform (CCWT), a novel color constancy statistical method is proposed in this paper. Analyses show that the CCWT subband coefficients of the standard light images can be well described by a multivariate Laplace distribution. Learning the distribution parameters from the white light images helps to established the standard multivariate Laplace distribution. Such standard distribution provides the criterion for light compensation, by which the bias light images can be translated to the standard light images. The maximum likelihood estimation results of the compensation light show that: our method is as good as the best performances of listed literatures, reducing the median error 0.1°, and the mean and maximum errors 0.3°.
- Color constancy /
- white balance /
- complementary color wavelets /
- color image
Recommended by Associate Editor SANG Nong
注释:

1) 本文责任编委桑农

HTML全文

图 1 色环与互补色小波

Fig. 1 The hue ring and the CCWT

下载: 全尺寸图片幻灯片

图 2 互补色小波的方向与相位, 每列对应$n = k\pi /8, k = 1, 2, \cdots, 8$中的一个方向, 每行对应$\theta = 0, 2\pi /3, 4\pi /3$中的一种相位

Fig. 2 Orientations and phases of the CCWT. Each column denotes one of the $n = k\pi /8, k = 1, 2, \cdots, 8$ orientations and each row denotes one of the $\theta = 0, 2\pi /3, 4\pi /3$ phases

下载: 全尺寸图片幻灯片

图 3 白色背景中一维边缘信号的互补色小波分解示例

Fig. 3 CCWT operators running over a line segment on the white background

下载: 全尺寸图片幻灯片

图 4 互补色小波子带统计特性

Fig. 4 Statistical characteristics of the CCWT subbands

下载: 全尺寸图片幻灯片

表 1 RAW格式数据库各种颜色恒常性算法结果的角度误差

Table 1 Angular errors for different color constancy methods on the COLOR CHECKER RAW database

方法	误差均值(°)	误差中值(°)	误差最大值(°)
White-patch ^[3]	7.4	5.6	40.6
Gray-world ^[4]	6.3	6.3	24.8
Shades-of-gray ^[5]	4.9	4.0	20.0
1st-order grey-edge ^[8]	5.2	4.5	19.7
2nd-order grey-edge ^[8]	5.0	4.4	16.9
Natural image statistics ^[24]	4.0	3.1	26.2
Gamut mapping ^[11]	4.1	2.3	23.2
Edge-based gamut mapping ^[12]	6.5	5.0	29.0
Exemplar-based ^[16]	3.1	2.3	16.3
Improved specular edge ^[7]	4.9	3.3	28.3
Multi-cue tree-structured ^[25]	3.3	2.2	18.2
AlexNet+SVR ^[18]	4.7	3.1	29.2
Using CNNs ^[34]	2.9	2.1	14.8
Bayesian ^[13]	4.7	3.5	24.5
Spatio-spectral statistics ^[15]	3.1	2.3	14.8
Proposed CCWT statistics	2.8	2.2	14.5

下载: 导出CSV

表 2 贝叶斯颜色恒常性算法结果比较

Table 2 Comparison between Bayesian color constancy methods

方法	误差均值(°)	误差中值(°)	误差最大值(°)
Spatio-spectral statistics ^[15]	3.1	2.3	14.8
CCWT with fixed $\alpha $	2.9	2.2	14.6
Proposed CCWT statistics	2.8	2.2	14.5

下载: 导出CSV

表 3 SFU HDR数据库各种颜色恒常性算法结果的角度误差

Table 3 Angular errors for different color constancy methods on the SFU HDR database

方法	误差均值(°)	误差中值(°)	最差25 %样本均值(°)
White-patch ^[3]	6.3	3.9	-
Gray-world ^[4]	8.0	7.4	15.0
Shades-of-gray ^[5]	5.7	3.9	12.7
1st-order grey-edge ^[8]	6.0	3.9	13.6
Corrected-moment ^[9]	4.0	3.2	-
Double-opponency ^[35]	6.2	3.5	14.0
Proposed CCWT statistics	4.4	3.1	9.8

下载: 导出CSV

参考文献(35)

[1]	West G, Brill M H. Necessary and sufficient conditions for Von Kries chromatic adaptation to give color constancy. Journal of Mathematical Biology, 1982, 15(2): 249-258 doi: 10.1007/BF00275077
[2]	Land E H, McCann J J. Lightness and retinex theory. JOSA, 1971, 61(1): 1-11 doi: 10.1364/JOSA.61.000001
[3]	Land E H. The retinex theory of color vision. Scientific American, 1977, 237(6): 108-128 doi: 10.1038/scientificamerican1277-108
[4]	Buchsbaum G. A spatial processor model for object colour perception. Journal of the Franklin Institute, 1980, 310(1): 1-26 doi: 10.1016/0016-0032(80)90058-7
[5]	Finlayson G D, Trezzi E. Shades of gray and colour constancy. In: Proceedings of the 12th Color Imaging Conference: Color Science and Engineering Systems, Technologies, Applications. Scottsdale, USA: The Society for Imaging Science and Technology, 2004. 37-41
[6]	张锐, 韩慧健, 梁秀霞, 方靖, 张彩明.基于色度一致性的室外场景光照参数估计.计算机科学, 2018, 45(3): 58-62, 82 http://d.old.wanfangdata.com.cn/Periodical/jsjkx201803010 Zhang Rui, Han Hui-Jian, Liang Xiu-Xia, Fang Jing, Zhang Cai-Ming. Illumination parameter estimation of outdoor scene using chromaticity consistency. Computer Science, 2018, 45(3): 58-62, 82 http://d.old.wanfangdata.com.cn/Periodical/jsjkx201803010
[7]	张玉萍, 杨学志, 方帅, 郑鑫, 李国强.改进的高光边缘颜色恒常性算法研究.仪器仪表学报, 2015, 36(9): 2076-2082 doi: 10.3969/j.issn.0254-3087.2015.09.020 Zhang Yu-Ping, Yang Xue-Zhi, Fang Shuai, Zheng Xin, Li Guo-Qiang. Research on improved specular edge color constancy algorithm. Chinese Journal of Scientific Instrument, 2015, 36(9): 2076-2082 doi: 10.3969/j.issn.0254-3087.2015.09.020
[8]	van de Weijer J, Gevers T, Gijsenij A. Edge-based color constancy. IEEE Transactions on Image Processing, 2007, 16(9): 2207-2214 doi: 10.1109/TIP.2007.901808
[9]	Finlayson G D. Corrected-moment illuminant estimation. In: Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney, NSW, Australia: IEEE, 2013. 1904-1911
[10]	Forsyth D A. A novel algorithm for color constancy. International Journal of Computer Vision, 1990, 5(1): 5-35 doi: 10.1007/BF00056770
[11]	Finlayson G D, Hordley S D, Tastl I. Gamut constrained illuminant estimation. International Journal of Computer Vision, 2006, 67(1): 93-109 doi: 10.1007/s11263-006-4100-z
[12]	Gijsenij A, Gevers T, van de Weijer J. Generalized gamut mapping using image derivative structures for color constancy. International Journal of Computer Vision, 2010, 86(2-3): 127-139 doi: 10.1007/s11263-008-0171-3
[13]	Gehler P V, Rother C, Blake A, Minka T, Sharp T. Bayesian color constancy revisited. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008. 1-8
[14]	Gijsenij A, Gevers T, van de Weijer J. Computational color constancy: survey and experiments. IEEE Transactions on Image Processing, 2011, 20(9): 2475-2489 doi: 10.1109/TIP.2011.2118224
[15]	Chakrabarti A, Hirakawa K, Zickler T. Color constancy with spatio-spectral statistics. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(8): 1509-1519 doi: 10.1109/TPAMI.2011.252
[16]	Joze H R V, Drew M S. Exemplar-based color constancy and multiple illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(5): 860-873 doi: 10.1109/TPAMI.2013.169
[17]	吴克伟, 杨学志, 谢昭.面向区域的非均匀光照估计方法.光学学报, 2016, 36(2): 233001 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201602042 Wu Ke-Wei, Yang Xue-Zhi, Xie Zhao. Regional-oriented non-uniform illumination estimation. Acta Optica Sinica, 2016, 36(2): 233001 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxxb201602042
[18]	Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25. Lake Tahoe, Nevada: MIT, 2012. 1097-1105
[19]	Hu Y M, Wang B Y, Lin S. FC⁴: fully convolutional color constancy with confidence-weighted pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA: IEEE, 2017. 330-339
[20]	唐贤伦, 杜一铭, 刘雨微, 李佳歆, 马艺玮.基于条件深度卷积生成对抗网络的图像识别方法.自动化学报, 2018, 44(5): 855-864 doi: 10.16383/j.aas.2018.c170470 Tang Xian-Lun, Du Yi-Ming, Liu Yu-Wei, Li Jia-Xin, Ma Yi-Wei. Image recognition with conditional deep convolutional generative adversarial networks. Acta Automatica Sinica, 2018, 44(5): 855-864 doi: 10.16383/j.aas.2018.c170470
[21]	随婷婷, 王晓峰.一种基于CLMF的深度卷积神经网络模型.自动化学报, 2016, 42(6): 875-882 doi: 10.16383/j.aas.2016.c150741 Sui Ting-Ting, Wang Xiao-Feng. Convolutional neural networks with candidate location and multi-feature fusion. Acta Automatica Sinica, 2016, 42(6): 875-882 doi: 10.16383/j.aas.2016.c150741
[22]	Qian Y L, Chen K, Nikkanen J, Kämäräinen J K, Matas J. Recurrent color constancy. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 5459-5467
[23]	Bianco S, Ciocca G, Cusano C, Schettini R. Automatic color constancy algorithm selection and combination. Pattern Recognition, 2010, 43(3): 695-705 doi: 10.1016/j.patcog.2009.08.007
[24]	Gijsenij A, Gevers T. Color constancy using natural image statistics and scene semantics. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(4): 687-698 doi: 10.1109/TPAMI.2010.93
[25]	Li B, Xiong W H, Hu W M, Funt B, Xing J L. Multi-cue illumination estimation via a tree-structured group joint sparse representation. International Journal of Computer Vision, 2016, 117(1): 21-47 doi: 10.1007/s11263-015-0844-7
[26]	Pridmore R W. Complementary colors theory of color vision: physiology, color mixture, color constancy and color perception. Color Research & Application, 2011, 36(6): 394-412 http://cn.bing.com/academic/profile?id=eb59ed7c79fa446e6be659163ed5d7fe&encoded=0&v=paper_preview&mkt=zh-cn
[27]	Pridmore R W. Complementary colors: the structure of wavelength discrimination, uniform hue, spectral sensitivity, saturation, chromatic adaptation, and chromatic induction. Color Research & Application, 2009, 34(3): 233-252 http://cn.bing.com/academic/profile?id=3d94177ce7b59ac5b8afdd5b602e7e7f&encoded=0&v=paper_preview&mkt=zh-cn
[28]	朱叶, 申铉京, 陈海鹏.基于彩色LBP的隐蔽性复制–粘贴篡改盲鉴别算法.自动化学报, 2017, 43(3): 390-397 http://www.cnki.com.cn/Article/CJFDTotal-MOTO201703006.htm Zhu Ye, Shen Xuan-Jing, Chen Hai-Peng. Covert copy-move forgery detection based on color LBP. Acta Automatica Sinica, 2017, 43(3): 390-397 http://www.cnki.com.cn/Article/CJFDTotal-MOTO201703006.htm
[29]	卢红阳, 刘且根, 熊娇娇, 王玉皞, 邓晓华.基于最大加权投影求解的彩色图像灰度化对比度保留算法.自动化学报, 2017, 43(5): 843-854 http://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201705016.htm Lu Hong-Yang, Liu Qie-Gen, Xiong Jiao-Jiao, Wang YuHao, Deng Xiao-Hua. Maximum weighted projection solver for contrast preserving decolorization. Acta Automatica Sinica, 2017, 43(5): 843-854 http://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201705016.htm
[30]	Chen Y, Li D, Zhang J Q. Complementary color wavelet: a novel tool for the color image/video analysis and processing. IEEE Transactions on Circuits and Systems for Video Technology, 2017, DOI: 10.1109/TCSVT.2017.2776239
[31]	Sendur L, Selesnick I W. Bivariate shrinkage functions for wavelet-based denoising exploiting interscale dependency. IEEE Transactions on Signal Processing, 2002, 50(11): 2744-2756 doi: 10.1109/TSP.2002.804091
[32]	Shi F, Selesnick I W. An elliptically contoured exponential mixture model for wavelet based image denoising. Applied and Computational Harmonic Analysis, 2007, 23(1): 131-151 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fbba68d31616341c71c2d318dc8e1ea0
[33]	Shi L, Funt B. Re-processed version of the Gehler color constancy dataset of 568 images. http://www.cs.sfu.ca/colour/data/, 2000.
[34]	Bianco S, Cusano C, Schettini R. Color constancy using CNNs. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Boston, MA, USA: IEEE, 2015. 81-89
[35]	Gao S B, Yang K F, Li C Y, Li Y J. Color constancy using double-opponency. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(10): 1973-1985 doi: 10.1109/TPAMI.2015.2396053