Natural Scene Recognition Based on Graph Edit Distance

Abstract:

Natural scene classification is a challenging pattern classification problem nowadays. The description of image plays a crucial role in the process of recognition. Many different approaches and feature extraction methodologies concerning scene classification have been proposed and applied in the last few years. This paper proposed a novel method of natural scene recognition based on graph edit distance (GED) in which scene images are represented by attributed graph. The vertex label is the features of regions and edge label is the features of public area of adjacent regions. This method used local representation as well as global way, realized the cooperation of global and local mechanisms. The proposed method approaches satisfactory categorization performances on the well-known scene classification datasets with 8 scene categories.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 4411-4416
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.4411
• Online since: February 2014
• Authors: Qiang Rong Jiang*, Jian Chang Song, Zhe Wu
• Keywords: Attributed Graph, GED, Natural Scene

References

[1] Boutell, M. 1, Luo, J. Natural scene classification using over complete ICA. 2005 IEEE International Conference on Multimedia and Expo, NY, USA, 6-8 July (2005).

DOI: 10.1109/icme.2005.1521358

[2] A. Payne and S. Singh. Indoor vs. outdoor scene classification in digital photographs. Pattern Recognition, Univ. of Exeter, UK Oct. (2005).

DOI: 10.1016/j.patcog.2004.12.014

[3] Oliva A and A Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 2001, 42(3): 145-175.

[4] Szummer, M. Picard, R.W. Indoor-outdoor image classification. 1998 IEEE International Workshop on Content-Based Access of Image and Video Database. 3 Jan. (1998).

DOI: 10.1109/caivd.1998.646032

[5] Quelhas P, et al. Modeling scenes with local descriptors and latent aspects. In: Proceedings of 10th IEEE International Conference on Computer Vision. Los Alamitos, CA, USA: IEEE Comput. Soc, 2005. 883-890.

DOI: 10.1109/iccv.2005.152

[6] Li Fei-fei and Perona P. A bayesian hierarchical model for learning natural scene categories. In: Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos, CA, USA: IEEE Comput. Soc, 2005. 524-531.

DOI: 10.1109/cvpr.2005.16

[7] Perina A, Cristani M and Murino V. Learning natural scene categories by selective multi-scale feature extraction. Image and Vision Computing, 2010, 28(6): 927-939.

DOI: 10.1016/j.imavis.2009.11.007

[8] Gokalp D and Aksoy S. Scene classification using bag-of-regions representations. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, NJ, USA: IEEE, 2007. 34-41.

DOI: 10.1109/cvpr.2007.383375

[9] A. G. H. J. Yang, Y. Jiang and C. Ngo. Evaluating bag-of-visual-words representations in scene classification. In Proc. of International Workshop on Multimedia Information Retrieval, pages 197-206, (2007).

DOI: 10.1145/1290082.1290111

[10] Vogel J, Schwaninger A, Wallraven C and Bulthoff H H. Categorization of natural scenes: local versus global information and the role of color. ACM Transactions on Applied Perception, 2007. 4(3): 1-21.

DOI: 10.1145/1278387.1278393

[11] Scholkopf B, Smola A J. A short introduction to learning with kernels. In: Proceedings of Advanced Lectures on Machine Learning, Berlin, Germany: Spring-Verlag, 2002. 41-64.

[12] Alatan, A.A. Efficient graph-based image segmentation via speeded-up turbo pixels. 2010 Proceedings of 17th IEEE International Conference on Image Processing. Page 3013-3016, 26-29 Sept. (2010).

DOI: 10.1109/icip.2010.5653963

[13] Shi Jian-Bo, Malik J. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000. 22(8): 888-905.

DOI: 10.1109/34.868688

[14] Koenen R, Pereira F. MPEG-7: a standardized description of audiovisual content. Signal Processing: Image Communication. 2000, 16(1-2): 5-13.

DOI: 10.1016/s0923-5965(00)00014-x

[15] Pinheiro A M G. Image descriptors based on the edge orientation. In: Proceedings of 4th International Workshop on Semantic Media Adaptation and Personalization, San Sebastian, Spain: IEEE Computer Society, 2009. 73-78.

DOI: 10.1109/smap.2009.27

[16] B. S. Manjunath, J. -R. Ohm, V. V. Vasudevan, and A. Yamada, Color and texture descriptors, IEEE Transactions.

[17] on Circuits and Systems for Video Technology, p.703–715, June (2001).

[18] T. Sikora, The MPEG-7 visual standard for content description an overview, IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, no. 6, p.696–702, June (2001).

DOI: 10.1109/76.927422

[19] J. Canny, A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, p.679–698, Nov. (1986).

DOI: 10.1109/tpami.1986.4767851

[20] T. Lindeberg, Edge detection and ridge detection with automatic scale selection, International Journal of Computer Vision, vol. 30, p.465–470, (1998).

[21] Le Saux, B. Bunke, H. Feature Selection for Graph-Based Image Classifiers. Pattern Recognition and Image Analysis. Page: 147-154. June (2005).

DOI: 10.1007/11492542_19

[22] Wagner, R.A. Fischer, M.J. The string-to-string correction problem. Journal of the Association for Computing Machinery. Page: 168-173. Jan. (1974).

[23] Shapiro L G and Haralick R M. A Metric for Comparing Relational Descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1985, 7(1): 90-94.

DOI: 10.1109/tpami.1985.4767621