基于层级分割的颜色恒常性算法

doi:10.6040/j.issn.1671-9352.0.2015.357

山东大学学报（理学版） ›› 2016, Vol. 51 ›› Issue (1): 101-105.doi: 10.6040/j.issn.1671-9352.0.2015.357

基于层级分割的颜色恒常性算法

王磊¹,谢江宁²

1.潍坊学院计算机工程学院, 山东潍坊 261061;2.山东大学计算机科学与技术学院, 山东济南 250101

收稿日期:2015-07-21 出版日期:2016-01-16 发布日期:2016-11-29
作者简介:王磊(1982— ),男,讲师,研究方向为图形图像处理、计算机视觉和软件工程. E-mail:wanglpqpq@gmail.com

Color constancy using hierarchy segments

WANG Lei¹, XIE Jiang-ning²

1. School of Computer Engineering, Weifang University, Weifang 261061, Shandong, China;
2. School of Computer Science and Technology, Shandong University, Jinan 250101, Shandong, China

Received:2015-07-21 Online:2016-01-16 Published:2016-11-29

摘要/Abstract

摘要： 颜色恒常性是指当照射物体表面的颜色光发生变化时,人们对该物体表面颜色的知觉仍然保持不变的视觉特性。灰度世界方法是一种常用的的颜色恒常方法,它假设客观世界中物体表面的平均反射比趋于灰色(灰度世界假设)。传统的灰度世界方法对整幅图像进行处理,然而并不是所有的图像都满足灰度世界假设。首先采用层级分割方法把图像分割成若干个片段,然后采用使用灰度世界方法处理各个片段,得到各个片段的估计结果;最后对这些估计结果进行聚类,得到最终结果。实验结果表明,该方法优于原始的灰度世界方法。与原始方法相比,平均误差降低至36.0%、中值误差降低至63.5%。本文所提出的算法优于目前领先的颜色恒常算法。

关键词: 贝叶斯方法, 层次分割, 图像分割, 颜色恒常性

Abstract: Color constancy is the ability to measure colors of objects independent of the color of the light source. A well-known color constancy method is based on the gray-world assumption which assumes that the average reflectance of surfaces in the world is achromatic. In this paper, instead of applying gray world method on the entire image, the images was segment into a lot of segments using a hierarchical segmentation method, and the simple gray world approach was applied on each segments. Then, estimated results from different segments were clustered together to get a final result. Experiment results show that the proposed algorithm outperforms the original gray world method. The mean error is reduced to 36.0% with respect to the original gray world method and the median error is reduced to 63.5%. Our method outperforms state-of-the-art color constancy algorithms and produces comparable results with the best published scores on the same dataset.

Key words: hierarchy segments, Bayes, color constancy, image segments

中图分类号:

TP391

王磊,谢江宁. 基于层级分割的颜色恒常性算法[J]. 山东大学学报（理学版）, 2016, 51(1): 101-105.

WANG Lei, XIE Jiang-ning. Color constancy using hierarchy segments[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(1): 101-105.

参考文献

[1] YANG J, STIEFELHAGEN R, MEIER U,WAIBEL A. Visual tracking formulti-modal human computer interaction[C] // Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. New York: ACM Press, 1998: 140-147.
[2] GEVERS T, SMEULDERS A W M. Pictoseek: Combining colour and shape invariant features for image retrieval[J]. IEEE Transactions on Image Processing, 2000, 9(1):102-119.
[3] FAIRCHILD M D. Color appearance models[J]. Packaging Engineering, 2005, 552(3):346.
[4] BUCHSBAUM G. A spatial processor model for object colour perception[J]. Journal of the Franklin Institute, 1980, 310(80):1-26.
[5] BARNARD K, FUNT B, CARDEI V. A comparison of computational color constancy algorithms, part one; theory and experiments with synthetic data[J]. IEEE Transactions on Image Processing, 2002, 11:972-984.
[6] 赵萍,王文举,陈伟.分层色彩校正算法研究[J].计算机工程与应用,2015,51(6):158-162. ZHAO Ping, WANG Wenju, CHEN Wei. Research on hierarchical color correction algorithm[J]. Computer Engineering and Application, 2015, 51(6):158-162.
[7] 张明,白松浩,邢姗姗.基于金字塔分解的自动色彩均衡算法[J].计算机工程,2015,(2):215-218. ZHANG Ming, BAI Songhao, XING Shanshan. Automatic color equalization algorithm based on pyramid decomposition[J]. Computer Engineering, 2015,(2):215-218.
[8] VAN DE SANDE K E A, UIJLINGS J R R, GEVERS T, et al. Segmentation as selective search for object recognition[C] // Proceedings of IEEE International Conference on Computer Vision. New York: IEEE, 2011: 1879-1886.
[9] SHI J, MALIK J. Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000, 22(8):888-905.
[10] FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision, 2004, 59(2):167-181.
[11] COMANICIU D, MEER P. Mean shift: a robust approach toward feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5):603-619.
[12] GEHLER P V, ROTHER C, BLAKE A, et al. Bayesiancolor constancy revisited[C] // Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2008: 1-8.
[13] LU R, GIJSENIJ A, GEVERS T, et al. Color constancy using 3D scene geometry[J]. IEEE International Conference on Computer Vision, 2009, 30(2):1749-1756.
[14] GIJSENIJ A, GEVERS T, WEIJER J V D. Generalized gamut mapping using image derivative structures for color constancy[J]. International Journal of Computer Vision, 2010, 86(2-3):127-139.
[15] GIJSENIJ A, GEVERS T. Color constancy using natural image statistics and scene semantics[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 33(4):687-698.
[16] LAND E H. The retinex theory of color vision[J]. Scientific American, 1977, 237(6):108-128.
[17] FINLAYSON G, TREZZI E. Shades of gray and colour constancy [C] // Proceedings of the 12th Color Imaging Conference: Color Science And Engineering Systems, Technologies, Applications.Springfield:SOC Imaging Science & Technology, 2004: 37-41.
[18] WEIJER J V D, GEVERS T, GIJSENIJ A. Edge-based color constancy[J]. IEEE Transactions on Image Processing, 2007, 16(9):2207-2214.
[19] FORSYTH D A. A novel algorithm for color constancy[J]. International Journal of Computer Vision, 1990, 5(1):5-35.
[20] SHI L, FUNT B. Re-processed version of the gehler color constancy dataset of 568 images[EB/OL].[2015-02-14]. http://www.cs.sfu.ca/~colour/data/

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于层级分割的颜色恒常性算法

Color constancy using hierarchy segments

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

多维度评价

本文评价

推荐阅读 0

[1]	刘战杰1,马儒宁1,邹国平1,钟宝江2,丁军娣3. 一种新的基于区域生长的彩色图像分割算法[J]. J4, 2010, 45(7): 76-80.
[2]	徐光柱1,刘鸣2,任东1,马义德3,刘晓丽1. 基于脉冲耦合神经网络的多区域图像分割[J]. J4, 2010, 45(7): 86-93.
[3]	董吉文,杨森,鲁守银 . 基于单目视觉的移动机器人导航方法[J]. J4, 2008, 43(11): 1-04 .