Abstract
Image structure representation is a vital technique in the image recognition. A novel image representation and recognition method based on directed complex network is proposed in this paper. Firstly, the key points are extracted from an image as the nodes to construct an initial complete undirected complex network. Then, the k-nearest neighbor evolution method is designed to form a series of directed networks. At last, the feature descriptor of the image is constructed by concatenating the structure features of each directed network to finally achieve image recognition. Experimental results demonstrate that the proposed method outperforms the traditional methods in image recognition and can describe the structure of images more effectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Backes AR, Martinez AS, Bruno OM (2011) Texture analysis using graphs generated by deterministic partially self-avoiding walks. Pattern Recogn 44(8):1684–1689
Jianguo Z, Tieniu T (2002) Brief review of invariant texture analysis methods. Pattern Recogn 35(3):735–747
Backes AR, Casanova D, Bruno OM (2009) A complex network-based approach for boundary shape analysis. Pattern Recogn 42(1):54–67
Backes AR, Bruno OM (2010) Shape classification using complex network and Multi-scale Fractal Dimension. Pattern Recogn Lett 31(1):44–51
Bin L, Edwin RH (2001) Structural graph matching using the EM algorithm and singular value decomposition. IEEE Trans Pattern Anal Mach Intell 23(10):1120–1136
Jin T, Chunyan Z, Bin L (2006) A new approach to graph seriation. In: Proceedings of International Conference on Innovative Computing, Information and Control (ICICIC’06) (2006)
Xinbo G, Bing X, Dacheng T et al (2008) Image categorization: Graph edit distance + edge direction histogram. Pattern Recogn 41(10):3179–3191
Amaral LAN, Ottino JM (2004) Complex networks. Eur phy J B 38:147–162
da Costa L, Rodrigues FA, Travieso G et al (2008) Characterization of complex networks: a survey of measurements. Adv Phy 56(1):167–242
Jin T, Bo J, Chin-Chen C et al (2012) Graph structure analysis based on complex network. Digital Signal Process 22:713–725
Bin L, Wilson RC, Hancock ER (2003) Spectral embedding of graphs. Pattern Recogn 36(10):2213–2223
Xin S, Xiaojun W (2011) A novel contour descriptor for 2D shape matching and its application to image retrieval. Image Vis Comput 29(4):286–294
Xiang B, Bo W, Cong Y et al (2012) Co-transduction for shape retrieval. IEEE Trans Image Process 21(5):2747–2757
Acknowledgments
This paper is supported by the National Natural Science Foundation of China (Nos. 61073116 & 61272152)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, Y., Tang, J., Luo, B. (2013). Image Representation and Recognition Based on Directed Complex Network Model. In: Yin, Z., Pan, L., Fang, X. (eds) Proceedings of The Eighth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA), 2013. Advances in Intelligent Systems and Computing, vol 212. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37502-6_115
Download citation
DOI: https://doi.org/10.1007/978-3-642-37502-6_115
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37501-9
Online ISBN: 978-3-642-37502-6
eBook Packages: EngineeringEngineering (R0)