Color reproduction method by support vector regression for color computer vision

被引:7
作者
Yang, Bo [1 ,2 ]
Chou, Hung-Yu [2 ]
Yang, Tsung-Hsun [2 ]
机构
[1] Chongqing Univ Sci & Technol, Sch Elect & Informat Engn, Chongqing 401331, Peoples R China
[2] Natl Cent Univ, Dept Opt & Photon, Chungli 320, Taiwan
来源
OPTIK | 2013年 / 124卷 / 22期
关键词
Color reproduction; Support vector regression; Successive 3 sigma filter; Least mean squared validating errors;
D O I
10.1016/j.ijleo.2013.04.036
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
In the color computer vision system, the nonlinearity of the camera and computer screen may result in different colors between the screen and the actual color of objects, which requires for color calibration. In this paper, support vector regression (SVR) method was introduced to reproduce the colors of the nonlinear imaging system. Firstly, successive 3 sigma method was used to eliminate the large errors found in the color measurement. Then, based on the training set measured in advance, SVR model of RBF kernel was applied to map the nonlinear imaging system. In this step, two important parameters (C, gamma) were optimized by the Least Mean Squared Validating Errors algorithm to get the best SVR model. Finally, this optimized model could predict the real values displayed on the screen. Compared with quadratic polynomial regression, BP neural network and relevance vector machine, the optimized SVR model has better ability in color reproduction performance and generalization. (C) 2013 Elsevier GmbH. All rights reserved.
引用
收藏
页码:5649 / 5656
页数:8
相关论文
共 22 条
[1]  
[Anonymous], 2000, NATURE STAT LEARNING, DOI DOI 10.1007/978-1-4757-3264-1
[2]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[3]  
Dai S.-H., 1992, RELIABILITY ANAL ENG, P448
[4]   A novel regressive algorithm based on relevance vector machine [J].
Ding, Er-rui ;
Zeng, Ping ;
Yao, Yong .
FOURTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, VOL 1, PROCEEDINGS, 2007, :463-+
[5]  
Drucker H, 1997, ADV NEUR IN, V9, P155
[6]  
Harr M.E., 1997, RELIABILITY BASED DE, P291
[7]  
Hong GW, 2001, COLOR RES APPL, V26, P76, DOI 10.1002/1520-6378(200102)26:1<76::AID-COL8>3.0.CO
[8]  
2-3
[9]  
[朱元泓 Zhu Yuanhong], 2004, [武汉大学学报. 信息科学版, Geomatics and Information Science of Wuhan University], V29, P836
[10]   The investigation of effects of digital proofing systems used in colour management on print quality with neural networks [J].
Kose, Erdogan ;
Sahinbaskan, Tuerkuen ;
Guler, Inan .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (01) :745-754