期刊文献+

利用色彩和谐模式辅助提取油画主题色 被引量:7

Extraction of Theme Colors from Oil Paintings Aided by Color Harmony Modules
下载PDF
导出
摘要 油画主题色体现了油画中所表达的主要色彩结构.文中提出一种油画主题色提取方法,首先根据色彩和谐模式预设主色相数量,把输入油画图像色相直方图与色彩和谐模式进行匹配,将色相环划分成若干色相带并依据匹配的模式类型提取主色相;然后利用主色相信息把输入图像划分成若干局部区域,对每个区域中的像素计算纯度直方图并从中提取出主纯度波峰,再用这些主纯度信息将上述局部区域细分为更小区域,对里面的像素计算明度直方图并提取出主明度;最后用得到的主色相、主纯度和主明度合成出候选主题色,并利用HSL欧氏距离在候选主题色中挑出最终主题色.与已有方法对比的实验结果表明,该方法在主题色中能保留数量少、但视觉上明显的像素色彩. Theme colors of oil painting represent the colorful keynote in the painting. In this paper we present a method for extracting theme colors from oil painting images. First, we predefine the number of main hues based on the color harmony type, and match the hue histogram with color harmony type. Second, we divide the hue ring into several segments with which the main hues can be detected. We assign pixels fallen into the hue segments with detected main hue values and calculate their saturation histograms from which the main saturations can be extracted. We further divide pixels associated with main saturations into subgroups and extract the main lightness from their histograms in the same manner. The candidates of theme colors are then composed by the components of the main hues, main saturations and main lightness and the theme colors are selected by use of Euclid distance in HSL space. Our method has the advantage over some of existing methods in preserving colors presented in a small number of pixels but visually significant.
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2014年第10期1576-1582,共7页 Journal of Computer-Aided Design & Computer Graphics
基金 国家自然科学基金(61379069) 国家科技支撑计划(2014BAK09B04) 国家社科基金重大项目(12&ZD231)
关键词 主题色 油画 色彩和谐 直方图 theme colors oil painting color harmony histograms
  • 相关文献

参考文献15

  • 1曹洪霞..油画色彩与摄影色彩的比较研究[D].南京艺术学院,2010:
  • 2王伟凝,蚁静缄,贺前华.可计算图像美学研究进展[J].中国图象图形学报,2012,17(8):893-901. 被引量:26
  • 3Heckbert P.Color image quantization for frame buffer display[C]//Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH.New York:ACM Press,1982:297-307. 被引量:1
  • 4Obrador P.Automatic color scheme picker for document templates based on image analysis and dual problem[C]// Proceedings of SPIE.Bellingham:Society of Photo-Optical Instrumentation Engineers,2006,6076:607-609. 被引量:1
  • 5Weeks A R,Hague G E.Color segmentation in the HSI color space using the k means algorithm[C]//Proceedings of SPIE.Bellingham:Society of Photo Optical Instrumentation Engineers,1997,3026:143-154. 被引量:1
  • 6MacQueen J.Some methods for classification and analysis of muhivariate observations[C]//Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability.Berkeley:University of California Press,1967:281-297. 被引量:1
  • 7Morse B S,Thornton D,Xia Q,et al.Image based color schemes[C]//Proceedings of IEEE International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2007:497-500. 被引量:1
  • 8Delon J,Desolneux A,Lisani J,et al.Automatic color palette[C]//Proceedings of IEEE International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2005:706-709. 被引量:1
  • 9O'Donovan P,Agarwala A,Hertzmann A.Color compatibility from large datasets[C]//Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH.New York:ACM Press,2011:Article No.63. 被引量:1
  • 10Matusda Y.Color design[M].[S.l.]:Asakura Shoten,1995. 被引量:1

二级参考文献40

  • 1郭云彪,尤新刚,张春田,周琳娜.面向信息隐藏的图像复杂度研究[J].电子学报,2006,34(6):1048-1052. 被引量:17
  • 2美国纽约摄影学院.美国纽约摄影学院摄影教材[M].李之聪,等译.北京:中国摄影出版社,2008. 被引量:3
  • 3Hoening F. Defining computational aesthetics [ C ]//Proceedings of Eurographics Workshop on Computational Aesthetics in Graphics, Visualization and Imaging. Switzerland: Eurographics Association, 2005 : 13-18. 被引量:1
  • 4Datta R, Joshi D, Li J,et al. Studying aesthetics in photographic images using a computational approach [ C ]//Proceedings of European Conference on Computer Vision. Heidelberg: Springer Berlin, 2006: 288-301. 被引量:1
  • 5Datta R, Wang J Z. ACQUINE: Aesthetic quality inference engine real-time automatic rating of photo aesthetics [ C ]//Proceedings of the ACM International Conference on Multimedia Information Retrieval. New York : Association for Computing Machinery, 2010: 421-424. 被引量:1
  • 6Wu Y, Bauckhage C, Thurau C. The good, the bad, and the ugly: predicting aesthetic image labels [ C]//Proceedings of 2010 20th International Conference on Pattern Recognition( ICPR 2010). Piscataway: Institute of Electrical and Electronics Engi- neers Inc, 2010 : 1586-1589. 被引量:1
  • 7Wong L K, Low K L. Saliency-enhanced image aesthetics class prediction [ C ]//Proceedings of 2009 IEEE International Conference on Image Processing( ICIP 2009). Piscataway: IEEE Computer Society, 2009:997-1000. 被引量:1
  • 8Luo Y, Tang X. Photo and video quality evaluation: focusing on the subject [ C ]//Proceedings of 2008 lOth European Conference on Computer Vision ( ECCV 2008 ). Heidelberg: Springer-Verlag, 2008,5304:386-399. 被引量:1
  • 9Li C, Tsuhan C. Aesthetic visual quality assessment of paintings [ J ]. IEEE Journal of Selected Topics in Signal Processing, 2009, 3(2) :236-252. 被引量:1
  • 10Obrador P, Anguera X, Oliveira R. The role of tags and image aesthetics in social image search [ C ]//Proceedings of 17th ACM International Conference on Multimedia, Workshop on Social Media(ACM MM). New York: Association for Computing Machinery, 2009:65-72. 被引量:1

共引文献58

同被引文献115

引证文献7

二级引证文献59

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部