[1]高彦宇,尹怡欣.D-S证据理论在图像情感标识中的应用[J].智能系统学报,2010,5(06):534-539.
 GAO Yan-yu,YIN Yi-xin.Application of the DempsterShafer theory to affective image annotation[J].CAAI Transactions on Intelligent Systems,2010,5(06):534-539.
点击复制

D-S证据理论在图像情感标识中的应用(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第5卷
期数:
2010年06期
页码:
534-539
栏目:
出版日期:
2010-12-25

文章信息/Info

Title:
Application of the DempsterShafer theory to affective image annotation
文章编号:
1673-4785(2010)06-0534-06
作者:
高彦宇尹怡欣
北京科技大学 信息工程学院,北京 100083
Author(s):
GAO Yan-yu YIN Yi-xin
School of Information Engineering, University of Science & Technology Beijing, Beijing 100083, China
关键词:
D-S证据理论图像情感标识情感因子分级语义
Keywords:
DempsterShafer theory affective image annotation affective factor hierarchical semantics
分类号:
TP391.4
文献标志码:
A
摘要:
图像情感标识就是为图像标注形容词性关键词,以反映用户对该图像的情感或印象.图像的视觉特征以及语义内容是决定用户对该图像情感理解的2项关键因素,而图像内容识别具有较高的不确定性,人类的情感理解也具有很强的主观性,因此采用DempsterShafer证据理论能较好实现图像视觉特征及语义内容到图像情感标识的不确定性推理.考虑到图像内容识别的不确定性,研究中按一定比例扩大了图像语义内容对各情感因子的不确定性区间,并构建了一个原型系统对自然风景图像进行自动标识.实验表明DempsterShafer证据理论在处理情感标识上是很有效的,而调整不确定性区间有助于进一步提高标识准确率.
Abstract:
Affective image annotation involves labeling an image with adjectives, so that those labels reflect the user’s emotional understanding of the image. The lowlevel visual features and the image semantic content are two decisive factors in the user’s emotional understanding of an image, while image content recognition is highly uncertain and affective understanding is strongly subjective. In the following study, the DempsterShafer theory was applied to represent the visual image characteristics and to model the uncertainty reasoning from those decisive factors to affective understanding. In response to the semantic recognition error, the uncertainty range of image contents to each affective factor was enlarged and a prototype affective annotation system was built to automatically label natural scenic images. Experimental results show that the DempsterShafer theory is promising for ambiguous annotation, and enlarging the uncertainty range is helpful for improving annotation precision.

参考文献/References:

[1]KOBAYASHI Y, KATO P. Multicontrast based texture model for understanding human subjectivity[C]//15th International Conference on Pattern Recognition. Barcelona, Spain, 2000, 3: 917922.
[2]毛峡,丁玉宽,牟田一弥.图像的情感特征分析及其和谐感评价[J]. 电子学报, 2001, 29(12A): 19231927.
MAO Xia, DING Yukuan, MUTA I. Analysis of affective characteristics and evaluation on harmonious feeling of image [J]. Acta Electronica Sinica, 2001, 29(12A): 1923 1927.
[3]CHO S B, LEE J Y. A humanoriented image retrieval system using interactive genetic algorithm[J]. IEEE Trans on Systems, Man, and Cybernetics, 2002, 32(3): 452458.
[4]WANG S F, WANG X F. A doublelevel emotion image retrieval model[J]. Journal of System Simulation, 2004, 16(9): 20742078.
[5]王伟凝, 贺前华. 基于色彩描述的图像情感语义查询[J]. 华南理工大学学报: 自然科学版, 2008, 36(1): 6066.
WANG Weining, HE Qianhua. Emotionbased image semantic query through color description[J]. Journal of South China University of Technology: Natural Science Edition, 2008, 36(1): 6066.
[6]BAEK S, HWANG M, CHUNG H, KIM P. Kansei factor space classified by information for Kansei image modeling[J]. Applied Mathematics and Computation, 2008, 205(2): 874882.
[7]SHIN Y, KIM Y, KIM E Y. Automatic textile image annotation by predicting emotional concepts from visual features[J]. Image and Vision Computing, 2010, 28(3): 526537.
[8]BLEKAS K, LIKAS A, GALATSANOS N P, LAGARIS I E. A spatiallyconstrained mixture model for image segmentation[J]. IEEE Transactions on Neural Networks, 2005, 16(2): 494498.
[9]MANJUNATH B S, MA W Y. Texture features for browsing and retrieval of image data [J]. IEEE Trans on PAMI, 1996, 18(8): 837842.
[10]陈立伟, 王文姝, 王颖芳. 基于模糊理论的关键词识别算法[J].应用科技, 2010, 9: 58.
 CHEN Liwei, WANG Wenshu, WANG Yingfang. Keyword recognition algorithm based on fuzzy theory[J]. Applied Science and Technology, 2010, 9: 58.
[11]WANG Y, HUANG S T. Reducing the number of subclassifiers for pairwise multicategory support vector machines[J]. Pattern Recognition Letters, 2007, 28: 20882093.

相似文献/References:

[1]马大中,张化光,冯 健,等.一种基于多传感器信息融合的故障诊断方法[J].智能系统学报,2009,4(01):72.
 MA Da-zhong,ZHANG Hua-guang,FENG Jian,et al.A fault diagnosis method based on multi-sensor information fusion[J].CAAI Transactions on Intelligent Systems,2009,4(06):72.
[2]徐耀松,王传为.果蝇算法和改进D-S证据理论的四轴飞行器障碍辨识[J].智能系统学报,2020,15(3):499.[doi:10.11992/tis.201809011]
 XU Yaosong,WANG Chuanwei.FOA and improved D-S evidence theory for quadcopter obstacle identification[J].CAAI Transactions on Intelligent Systems,2020,15(06):499.[doi:10.11992/tis.201809011]

备注/Memo

备注/Memo:
收稿日期:2010-01-03.
基金项目:国家自然科学基金资助项目(60374032).
通信作者:高彦宇.E-mail:yannie.g@126.com.
作者简介:
高彦宇,女,1975年生,博士,讲师.主要研究方向为图像处理与模式识别、感性工学、人工智能.
尹怡欣,男,1957年生,教授,博士生导师,博士.主要研究方向为智能控制及自适应控制、人工生命、情感计算.
更新日期/Last Update: 2011-03-03