A Method of Image Affective Semantic Classification Based on Attribution Reduction

Abstract:

In study of image affective semantic classification, one problem is the low classification accuracy caused by low-level redundant features. To eliminate the redundancy, a novel image affective classification method based on attributes reduction is proposed. In this method, a decision table is built from the extraction of image features first. And then valid low-level features are determined through the feature selection process using the rough set attribute reduction algorithm. Finally, the semantic recognition is done using SVM. Experiment results show that the proposed method improves the accuracy in image affective semantic classification significantly.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 4820-4824
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.4820
• Online since: May 2014
• Authors: Ying Xia*, Le Mi, Hae Young Bae
• Keywords: Affective Semantic, Attribute Reduction, Image Classification, Rough Set (RS)

References

[1] EAKINS J P in : Automatic image content retrieval—are we getting anywhere, edited by Proceedings of the Third International Conference on Electronic Library and Visual Information Research. Milton Keynes: De Montfort University, Aslib. Vol. 123-135(1996).

[2] STEFANIE S, WOLFGANG G S in: Collective indexing of emotions in images: a study in emotional information retrieval, edited by Journal of the American Society for Information Science and Technology. Vol. 863-876(2009), p.60.

DOI: 10.1002/asi.21043

[3] Shangfei Wang and Xunfa Wang in : Atrificial affective model based on dimension, though , edited by Journal of university of science and technology of China. Vol. 83-91(2001).

[4] DAI Ying in: Intention-based image retrieval with or without a query image, edited by Proceedings of the 10th International Multimedia Modeling Conference, DC, USA: IEEE Computer Society Washington, Vol. 26-32(2004).

DOI: 10.1109/mulmm.2004.1264963

[5] Yanyu Gao, Xinping Wang and Yixin Yin in: Research on Affective Annotation for Natural Scene Images, edited by Journal of Chinese Computer Systems, Vol. 768-769(2011), p.32.

[6] Pinting Li, Yuexiang Shi and Huangguan Dai in : Household design classification based on color feature edited by Computer engineering. Vol. 224-226, 229(2011), p.37.

[7] WU Li-di, QIN Liang-xi and CHEN Yong-sheng, in: Study on image emotional classification based on decision tree and fuzzy SVM, edited by Micro computer information. Vol. 211-213(2011), p.27.

[8] Plutchik R in: The Nature of Emotions, edited by American Scientist, Vol. 344-350(2001), p.89.

[9] EKMAN P in: An argument for basic emotions, edited by Cognition and Emotion, Vol. 169-200(1992), p.6.

[10] Pawlak, Z in : Rough Sets, edited by International Journal of Computer and Information Science, Vol. 341-356, (1982) , p.11.

[11] Zengrong Liu, Xuli Yu and Zhi Li in: Image affective semantic research based on feature fusion, edited by Journal of taiyuan university of technology. Vol. 553-557(2012), p.43.