[1]张晶,薛澄岐,沈张帆,等.基于认知分层的图像复杂度研究[J].东南大学学报(自然科学版),2016,46(6):1149-1154.[doi:10.3969/j.issn.1001-0505.2016.06.007]
 Zhang Jing Xue Chengqi Shen Zhangfan Wang Haiyan Zhou Lei Zhou Xiaozhou Chen Xiaojiao.Study on image complexity based on cognitive layering method[J].Journal of Southeast University (Natural Science Edition),2016,46(6):1149-1154.[doi:10.3969/j.issn.1001-0505.2016.06.007]
点击复制

基于认知分层的图像复杂度研究()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
46
期数:
2016年第6期
页码:
1149-1154
栏目:
出版日期:
2016-11-20

文章信息/Info

Title:
Study on image complexity based on cognitive layering method
作者:
张晶薛澄岐沈张帆王海燕周蕾周小舟陈晓皎
东南大学机械工程学院, 南京 211189
Author(s):
Zhang Jing Xue Chengqi Shen Zhangfan Wang Haiyan Zhou Lei Zhou Xiaozhou Chen Xiaojiao
School of Mechanical Engineering, Southeast University, Nanjing 211189, China
关键词:
图像复杂度 认知分层 人机交互 图像属性 映射方法
Keywords:
image complexity cognitive layering human computer interaction image attributes mapping method
分类号:
TP-391
DOI:
10.3969/j.issn.1001-0505.2016.06.007
摘要:
为揭示图像属性与图像复杂度之间的编码规律,从认知分层角度对图像复杂度进行了研究.基于由浅入深的认知加工次序,将图像复杂度分为呈现复杂度(CP)、语义复杂度(CS)和记忆复杂度(CM),分别对应图像的视觉属性、语义属性和解码属性,并建立复杂度分层映射模型.以地铁交通图为例,提取图像中3种复杂度后按低、中、高水平重新编码,并结合眼动追踪技术进行了视觉搜索实验.实验结果表明:高记忆复杂度编码的反应时最短,对认知绩效的影响最大;高语义复杂度编码易造成视觉干扰,需结合高记忆复杂度来提高认知绩效;高呈现复杂度编码能有效降低被试的认知负荷,提高搜索效率.实验结果证实了图像复杂度分层的合理性,为信息化图像的复杂度设计提供了参考.
Abstract:
To investigate the encoding rules between image attributes and image complexity, the image complexity was studied from the perspective of the cognitive layering theory. Based on the gradual order of the cognitive process, the image complexity was divided into CP(complexity of presentation), CS(complexity of semantics)and CM(complexity of memory), mapping to the visual attributes, semantic attributes and decoding attributes. Then, a layering mapping model of image complexities was presented. Taking the metro map image as example, three complexities in the image were extracted and recoded into three levels as low, medium, high and then a visual search experiment was conducted by the eye-tracking technique. Experimental results show that the three complexities have many obvious corresponding features in layering encoding. The reaction time of high level CM encoding is the shortest, suggesting that the CM has the greatest effect on the cognitive efficiency. According to the large visual noise in high level CS encoding, the CS should be encoded with high level CM to improve the cognitive efficiency. The high level CP encoding can decrease subjects’ cognitive load, which favors the improvement of search efficiency. Experimental results confirm the rationality of layering image complexity, thus providing a reference for the complexity design of information images.

参考文献/References:

[1] Rigau J, Feixas M, Sbert M. An information-theoretic framework for image complexity [C]//Computational Aesthetics 2005:Eurographics Workshop on Computational Aesthetics in Graphics, Visualization and Imaging. Girona, Spain, 2005: 177-184.
[2] Mario I, Chacon M, Alma D, et al. Image complexity measure: A human criterion free approach[C]//IEEE Fuzzy Information Processing Society. Ann Arbor, Michigan, USA, 2005: 241-246.
[3] Silva M P D, Courboulay V, Estraillier P. Image complexity measure based on visual attention[C]//IEEE Image Processing. Brussels, Belgium, 2011: 3281-3284.
[4] Huo J. Image complexity and visual working memory capacity[J]. Emerging Trends and Advanced Technologies for Computational Intelligence, 2016, 647: 301-314. DOI:10.1007/978-3-319-33353-3-16.
[5] Huo J. An image complexity measurement algorithm with visual memory capacity and an EEG study[C]//SAI Computing Conference. London, UK,2016: 264-268. DOI:10.1109/sai.2016.7555993.
[6] Corchs S E, Ciocca G, Bricolo E, et al. Predicting complexity perception of real world images[J]. PLoS One, 2016, 11(6): e0157986. DOI:10.1371/journal.pone.0157986.
[7] Chen Y Q, Duan J, Zhu Y, et al. Research on the image complexity based on neural network[C]// 2015 International Conference on Machine Learning and Cybernetics. Hangzhou, China, 2015:285-300. DOI:10.1109/icmlc.2015.7340938.
[8] Al-Khatib W, Day Y F, Ghafoor A, et al. Semantic modeling and knowledge representation in multimedia databases[J]. IEEE Transactions on Knowledge and Data Engineering, 1999, 11(1):64-80. DOI:10.1109/69.755616.
[9] 李晶, 薛澄岐, 王海燕, 等. 均衡时间压力的人机界面信息编码[J]. 计算机辅助设计与图形学学报, 2013, 25(7): 1022-1028.
  Li Jing, Xue Chengqi, Wang Haiyan, et al. Encoding information of human-computer interface for equilibrium of time pressure[J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(7):1022-1028.(in Chinese)
[10] Lin S W, Lo Y S, Huang T K. Visual complexity and figure-background color contrast of E-commerce websites: Effects on consumers’ emotional responses[C]//49th International Conference on System Sciences. Hawaii,USA, 2016: 3594-3603. DOI:10.1109/hicss.2016.449.
[11] Harper S, Jay C, Michailidou E, et al. Analysing the visual complexity of web pages using document structure[J].Behaviour& Information Technology, 2012, 32(5): 491-502. DOI:10.1080/0144929x.2012.726647.
[12] Reder L M, Liu X L, Keinath A, et al. Building knowledge requires bricks, not sand: The critical role of familiar constituents in learning[J]. Psychonomic Bulletin & Review, 2016, 23(1): 271-277. DOI:10.3758/s13423-015-0889-1.
[13] Dewitt M R, Knight J B, Hicks J L, et al. The effects of prior knowledge on the encoding of episodic contextual details[J]. Psychonomic Bulletin & Review, 2012, 19(2):251-257. DOI:10.3758/s13423-011-0196-4.

备注/Memo

备注/Memo:
收稿日期: 2016-02-17.
作者简介: 张晶(1988—),女,博士生;薛澄岐(联系人),男,博士,教授,博士生导师, ipd-xcq@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(71471037, 71271053)、江苏省普通高校研究生科研创新计划资助项目(KYLX15-0062).
引用本文: 张晶,薛澄岐,沈张帆,等.基于认知分层的图像复杂度研究[J].东南大学学报(自然科学版),2016,46(6):1149-1154. DOI:10.3969/j.issn.1001-0505.2016.06.007.
更新日期/Last Update: 2016-11-20