面向视觉感知的图像情感识别及其在推荐系统中的应用

doi:10.3772/j.issn.1000-0135.2019.04.010

情报学报

2019, Vol. 38

Issue (4): 420-431 DOI: 10.3772/j.issn.1000-0135.2019.04.010

情报用户与行为研究

本期目录 | 过刊浏览 | 高级检索

面向视觉感知的图像情感识别及其在推荐系统中的应用

陈芬, 何源, 汤丽萍

南京理工大学经济管理学院，南京 210094

Emotional Recognition of Visual-perception Oriented Images and Its Application in the Recommendation System

Chen Fen, He Yuan, Tang Liping

School of Economics and Management, Nanjing University of Science and Technology, Nanjing 210094

摘要
图/表
参考文献
相关文章 (2)

全文: PDF (24394 KB) HTML (161 KB)
输出: BibTeX | EndNote (RIS)

摘要视觉信息是人们获取外界信息的重要来源。作为视觉信息的主要表现形式之一，图像受到了广泛关注。本文首先针对颜色直方图忽略空间信息的问题，基于图像分块思想，利用图像区域不同、引起的关注程度不同的原理，引入Itti视觉注意模型，进行图像显著图的提取，基于显著图计算各分块的加权直方图。其次，根据视觉感知理论，提取多种图像情感信息特征，结合低层的颜色、纹理和形状特征以及高层的面部表情特征，生成复合的图像情感特征描述向量。最后，将本文提出的情感识别模型用于基于情感的电影推荐，结合电影海报及剧情简介文本，进行基于图文结合的电影情感识别，为用户推荐符合其情感需求的电影。本文通过融合基于心理认知的特征及面部表情等诸多特征，实现了更加完善的视觉情感描述，在一定程度上缩小了“语义鸿沟”。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈芬
	何源
	汤丽萍

关键词 ：情感分类, 特征提取, 视觉感知, 情感语义, SVM算法

收稿日期: 2018-08-17

引用本文:

陈芬, 何源, 汤丽萍. 面向视觉感知的图像情感识别及其在推荐系统中的应用[J]. 情报学报, 2019, 38(4): 420-431.
Chen Fen, He Yuan, Tang Liping. Emotional Recognition of Visual-perception Oriented Images and Its Application in the Recommendation System. 情报学报, 2019, 38(4): 420-431.

链接本文:

https://qbxb.istic.ac.cn/CN/10.3772/j.issn.1000-0135.2019.04.010 或 https://qbxb.istic.ac.cn/CN/Y2019/V38/I4/420

1 EkmanP. An argument for basic emotions[J]. Cognition and Emotion, 1992, 6(3-4): 169-200.
2 MikelsJ A, FredricksonB L, LarkinG R, et al. Emotional category data on images from the international affective picture system[J]. Behavior Research Methods, 2005, 37(4): 626-630.
3 黄崑, 赖茂生. 图像情感特征的分类与提取[J]. 计算机应用, 2008, 28(3): 659-661.
4 李娉婷, 石跃祥, 戴皇冠. 基于颜色特征的家居设计图分类[J]. 计算机工程, 2011, 37(16): 224-226.
5 曹建芳, 陈俊杰, 李海芳. 基于改进的OCC情感模型的自然风景图像分类研究[J]. 计算机应用与软件, 2014, 31(6): 181-184.
6 张海波, 张春艳, 商书元, 等. 男T 恤图像情感语义空间研究[J]. 纺织科技进展, 2016(6): 53-55.
7 SiersdorferS, MinackE, DengF, et al. Analyzing and predicting sentiment of images on the social web[C]// Proceedings of the 18th ACM International Conference on Multimedia. New York: ACM Press, 2010: 715-718.
8 ShinY, KimE Y, SungT E. Affect-based retrieval of landscape images using probabilistic affective model[C]// Proceedings of the International Conference on Human-Computer Interaction. Heidelberg: Springer, 2013: 362-371.
9 SeoS, KangD. Study on predicting sentiment from images using categorical and sentimental keyword-based image retrieval[J]. Journal of Supercomputing, 2016, 72(9): 3478-3488.
10 ParkM W, KoD, HwangH, et al. Image classification using color and spatial frequency in terms of human emotion[C]// Proceedings of the International Conference on Future Information Technology. Singapore: Springer, 2017, 448: 91-96.
11 LeeG, KwonM, KavuriS, et al. Action-perception cycle learning for incremental emotion recognition in a movie clip using 3D fuzzy GIST based on visual and EEG signals[J]. Integrated Computer-Aided Engineering, 2014, 21(3): 295-310.
12 LiZ H, FanY Y, LiuW H, et al. Image sentiment prediction based on textual descriptions with adjective noun pairs[J]. Multimedia Tools and Applications, 2018, 77(1): 1115-1132.
13 LuX, SuryanarayanP, R B JrAdams, et al. On shape and the computability of emotions[C]// Proceedings of the 20th ACM International Conference on Multimedia. New York: ACM Press, 2012: 229-238.
14 JoshiD, DattaR, FedorovskayaE, et al. Aesthetics and emotions in images[J]. IEEE Signal Processing Magazine, 2011, 28(5): 94-115.
15 WangX H, JiaJ, YinJ M, et al. Interpretable aesthetic features for affective image classification[C]// Proceedings of the IEEE International Conference on Image Processing. IEEE, 2014: 3230-3234.
16 曹建芳, 陈俊杰, 李海芳. 基于Adaboost-BP神经网络的图像情感分类方法研究[J]. 山西大学学报(自然科学版), 2013, 36(3): 331-337.
17 刘颍霜. 基于LFCM-SVM的版画情感映射改进算法研究[D]. 云南: 云南大学, 2015.
18 庄千料. 基于概率神经网络的图像细粒度情感分类[D]. 上海: 东华大学, 2017.
19 KoE, KimE Y. Recognizing the sentiments of web images using hand-designed features[C]// Proceedings of the IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing. IEEE, 2015: 156-161.
20 ZhuoY. Research on perception-oriented image scene and emotion categorization[J]. The Open Automation and Control Systems Journal, 2015, 7: 2070-2073.
21 IttiL, KochC. Feature combination strategies for saliency-based visual attention systems[J]. Journal of Electronic Imaging, 2001, 10(1): 161-169.
22 LoweD G. Distinctive image features from scale-invariant keypoints[M]. Kluwer Academic Publishers, 2004.
23 GeusebroekJ M, BurghoutsG J, SmeuldersA W M. The Amsterdam library of object images[J]. International Journal of Computer Vision, 2005, 61(1): 103-112.
24 PengX J, WangL M, WangX X, et al. Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice[J]. Computer Vision and Image Understanding, 2016, 150: 109-125.
25 Microsoft cognitive services[EB/OL]. [2018-04-15]. https://www.microsoft.com/cognitive-services/en-us/apis.
26 Schr?derM. Evidence for a three-factor theory of emotions[C]// Proceedings of the Conference on the European Cetacean Society. 2017: 716-721.
27 ValdezP, MehrabianA. Effects of color on emotions[J]. Journal of Experimental Psychology: General, 1994, 123(4): 394-409.
28 HaralickR M, ShanmugamK, DinsteinI H. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6): 610-621.
29 AnwerR M, VázquezD, LópezA M. Opponent colors for human detection[C]// Proceedings of the 5th Iberian conference on Pattern recognition and image analysis. Heidelberg: Springer, 2011: 363-370.
30 LangP J, BradleyM M, CuthbertB N. International affective picture system (IAPS): Affective ratings of pictures and instruction manual[R]. University of Florida, 2008: No. A-8.
31 吕微微. 基于情感的图像分类算法研究与实现[D]. 北京: 北京交通大学, 2012.
32 刘硕研. 面向感知的图像场景及情感分类算法研究[D]. 北京: 北京交通大学, 2011.
33 宋璇. 图像情感分类算法研究[D]. 秦皇岛: 燕山大学, 2017.
34 吕鹏霄. 图像情感分类研究[D]. 秦皇岛: 燕山大学, 2014.