Please wait a minute...
浙江大学学报(工学版)
J4  2013, Vol. 47 Issue (8): 1486-1492    DOI: 10.3785/j.issn.1008-973X.2013.08.024
计算机技术﹑电信技术     
基于艺术风格相似性规则的绘画图像分类
杨冰, 许端清, 杨鑫, 赵磊, 唐大伟
浙江大学 计算机学院网络与媒体实验室,310027
Painting image classification based on aesthetic style similarity rule
YANG Bing, XU Duan-qing, YANG Xin, ZHAO Lei, TANG Da-wei
Network and Multimedia Lab, Computer Science College, Zhejiang University, Hangzhou, 310027, China
 全文: PDF  HTML
摘要：

针对传统分类方法中直接建立描述符描述绘画的艺术风格而忽略艺术风格这一对象本身所具有的属性的问题,从人脑认知机制出发,将艺术风格的描述建立于特征向量及相似性原理的基础之上.算法基于相似性原理,通过挖掘艺术风格自身属性,建立艺术风格相似性规则.在遵守相似性规则的基础上,对艺术领域中普遍认可的风格特征进行量化,建立图像的自相似性描述符,采用距离函数计算出图像与其他所有样本图像之间的相似性系数,将由相似性系数构成的相似性矩阵作为该图像的风格相似性矩阵,采用Adaboost分类器对未知样本做出判断.结果表明艺术风格相似性规则的有效性,在不同艺术风格绘画图像上的分类实验也得到较好的结果.
Abstract:

For the problem of the traditional classification methods that often directly construct descriptors and ignoring the inherent properties of aesthetic style, starting from human brain cognitive mechanisms, we propose to describe the aesthetic style on the basis of the feature vector and similarity principle. We create aesthetic style similarity rule (ASSR) based on similarity principle and deep analysis of the inherent properties of aesthetic style. Follow ASSR, we then quantify style features that are generally accepted in realm of art to build the image self-similarity descriptor. The distance function is used in our method to compute the similarity coefficient between one image to all other images. Finally, the similarity matrix composed of similarity coefficients could be treated as the aesthetic style similarity descriptor for the image, and Adaboost classifier is taken to evaluate the unknown images. The results demonstrate the efficiency of ASSR and our method for the painting image classification with different aesthetic style obtains good performance.
出版日期: 2013-08-01
:  TP 391.4  
基金资助:

数字博物馆核心关键技术攻关资助项目(2012BAH03F02)|国家“973”重点基础研究发展计划资助项目(2012CB725305).
通讯作者: 许端清,男,教授.     E-mail: xdq@zju.edu.cn
作者简介: 杨冰(1985—),女,博士生.从事模式识别、图像分类的研究.E-mail: ybily061821@126.com.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

杨冰, 许端清, 杨鑫, 赵磊, 唐大伟. 基于艺术风格相似性规则的绘画图像分类[J]. J4, 2013, 47(8): 1486-1492.

YANG Bing, XU Duan-qing, YANG Xin, ZHAO Lei, TANG Da-wei. Painting image classification based on aesthetic style similarity rule. J4, 2013, 47(8): 1486-1492.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2013.08.024    或    http://www.zjujournals.com/eng/CN/Y2013/V47/I8/1486

［1］ BOSCH A, ZISSERMAN A, MUOZ X. Scene classification using a hybrid generative/discriminative approach ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(4): 712-727.

［2］ 任建峰,郭雷,李刚.多类支持向量机的自然图像分类［J］.西北工业大学学报,2005,23(3): 295-298.

REN Jian-feng,GUO Lei,LI Gang. Improving scene image classification with multi-class SVMs ［J］.Journal of Northwestern Polytechnical University,2005,23(3): 295-298.

［3］ 任桢.图像分类任务的关键技术研究［D］.哈尔滨:哈尔滨工程大学,2010.

REN Zhen. Key techniques studying on image classification ［D］.Harbin: Harbin Engineering University, 2010.

［4］ LI C C, CHEN T. Aesthetic visual quality assessment of paintings ［J］.  IEEE Journal of Selected Topics in Signal Processing, 2009, 3(2): 236-252.

［5］ DATTA R, JOSHI D, LI J, et al. Studying aesthetics in photographic images using a computational approach ［C］∥ The 6th European Conference on Computer Vision. Dublin: Springer-Verlag London, 2006, 288-301.

［6］ MOORTHY A K, OBRADOR P, OLIVER N. Towards computational models of visual aesthetic appeal of consumer videos ［C］∥ The 11th European Conference on Computer Vision (ECCV’10). Heraklion: Springer-Netherlands,2010, 6315: 1-14.

［7］ LI J, WANG J Z. Studying digital imagery of ancient paintings by mixtures of stochastic models ［J］. IEEE Transactions on Image Processing, 2004, 13(3): 340-353.

［8］ YELIZAVETA M, SENG T C, RAMESH J. Semi-supervised annotation of brushwork in paintings domain using serial combinations of multiple experts ［C］∥ Proceedings of the 14 th annual ACM international conference on Multimedia. New York: ACM Press,2006, 529-538.

［9］ KEREN D. Recognizing image “style” and activities in video using local features and nave bayes ［J］. Pattern Recognition Letters, 2003, 24(16): 2913-2922.

［10］ YOAV F, SCHAPIRE R E. A decision-theoretic generalization of online learning and an application to boosting ［J］. Journal of Computer and System Sciences, 1997, 13(55): 119-139.

［11］ DRUCKER H, SCHAPIRO R E, SIMARD P. Boosting performance in neural networks ［J］. International Journal of Pattern Recognition and Artificial Intelligence, 1993, 7(4): 705-719.

［12］ FREUND Y, SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting ［C］∥ In Proceedings of the Second European Conference on Computational Learning Theory (EuroCOLT’95). Barcelona: Springer, 1995, 23-37.

［13］ SCHAPIRE R E. A brief introduction to boosting ［C］∥ Proceedings of the 16th International Joint Conference on Artificial Intelligence (IJCAI’99), Stockholm: Morgan Kaufmann Publisher, 1999, 1401-1406.

［14］ 黄蓉.论刘松年工笔人物画的艺术风格［D］.扬州:扬州大学,2010.

HUANG Rong.The artistic style research on meticulous portrait of Liu Songnian ［D］.Yangzhou: Yangzhou University,2010.

［15］ 孙美君.中国水墨画的设色扩散与风格化绘制研究［D］.天津:天津大学,2009.

SUN Mei-jun. Research on the pigments diffusing and stylistic rendering of chinese painting ［D］.Tianjin: Tianjin University, 2009.

［16］ 王先岳.写生与新山水画图式风格的形成［D］.北京:中国艺术研究院,2010.

Wang xian-yue. Painting from nature and on the formation o f the schemata style in the new landscape painting ［D］. Beijing: Chinese National Academy of Arts, 2010.

［17］ VARMA M, ZISSERMAN A. Classifying images of materials: achieving viewpoint and illumination independence ［C］∥ The 7th European Conference on Computer Vision (ECCV’02), Copenhagen: Springer, 2002, 255-271.

［18］ GEHLER P V, NOWOZIN S. On feature combination for multiclass object classification ［C］∥ IEEE International Conference on Computer Vision (ICCV’09), Kyoto: IEEE Computer Society, 2009, 221-228.
[1] 徐嵩,孙秀霞,何衍. 利用直线段成像特性的摄像机畸变迭代标定方法[J]. J4, 2014, 48(3): 404-413.
[2] 谢天, 解利军, 宋广华, 郑耀. 基于平面颜色分布的增强现实自然特征注册算法[J]. J4, 2013, 47(12): 2243-2252.
[3] 杨帮华, 何美燕, 刘丽, 陆文宇. 脑机接口中基于BISVM的EEG分类[J]. J4, 2013, 47(8): 1431-1436.
[4] 楼晓俊, 孙雨轩, 刘海涛. 聚类边界过采样不平衡数据分类方法[J]. J4, 2013, 47(6): 944-950.
[5] 孟子博, 姜虹, 陈婧, 袁波, 王立强. 基于特征剪裁的AdaBoost算法及在人脸检测中的应用[J]. J4, 2013, 47(5): 906-911.
[6] 何智翔, 丁晓青, 方驰, 文迪. 基于LBP和CCS-AdaBoost的多视角人脸检测[J]. J4, 2013, 47(4): 622-629.
[7] 刘晓芳,叶修梓,张三元,张引. 并行磁共振图像的非二次正则化保边性重建[J]. J4, 2012, 46(11): 2035-2043.
[8] 张远辉,韦巍. 在线角速度估计的乒乓球机器人视觉测量方法[J]. J4, 2012, 46(7): 1320-1326.
[9] 施锦河, 沈继忠, 王攀. 四类运动想象脑电信号特征提取与分类算法[J]. J4, 2012, 46(2): 338-344.
[10] 张大尉, 朱善安. 基于核邻域保持判别嵌入的人脸识别[J]. J4, 2011, 45(10): 1842-1847.
[11] 舒振宇, 汪国昭. 基于张量投票的快速网格分割算法[J]. J4, 2011, 45(6): 999-1005.
[12] 徐舒畅, 张三元, 张引. 基于彩色图像的皮肤色素浓度提取算法[J]. J4, 2011, 45(2): 253-258.
[13] 佘青山, 孟明, 罗志增, 马玉良. 基于多核学习的下肢肌电信号动作识别[J]. J4, 2010, 44(7): 1292-1297.
[14] 薛凌云, 段会龙, 向学勤, 范影乐. 基于FitzHughNaguno神经元随机共振机制的图像复原[J]. J4, 2010, 44(6): 1103-1107.
[15] 张远辉, 韦巍, 虞旦. 基于实时图像的乒乓机器人Kalman跟踪算法[J]. J4, 2009, 43(09): 1580-1584.