Abstract
Semantic image classification is a hot issue of image mining. Information of spatial relations between objects in an image is one of the important semantic information of an image. However, the previous researches have not made full use of the spatial relations for image modeling and classification. In addition, to classify the images with Bayesian network, the accuracy of conditional probability estimation may be insufficient, because the learning methods of spatial contextual models have usually used a limited number of training samples. In this work, the semantic image modeling based on attributed relational graph has been proposed, in which the distance measure method between images was presented, therefore the object information and spatial relational information could be fully utilized. Then, the semantic distance between images based on attributed relational graph could be calculated for the support vector machine to obtain the joint conditional probability distribution of Bayesian network. Therefore the probabilistic estimation problem under the sparse training samples could be solved, and the accuracy of semantic image classification with Bayesian network was improved. Experimental results show the validity and reliability of this proposed method.
Similar content being viewed by others
References
Aksoy S, Koperski K, Tusk C et al (2005) Learning Bayesian classifiers for scene classification with a visual grammar [J]. IEEE Trans Geosci Remote Sens 43(3):581–589. doi:10.1109/TGRS.2004.839547
Aksoy S, Tusk C, Koperski K, et al. (2003) Scene modeling and image mining with a visual grammar [J]. Frontiers of Remote Sensing Information Processing, 35–62. doi:10.1142/9789812796752_0003
Athanasiadis T, Mylonas P, Avrithis Y et al (2007) Semantic image segmentation and object labeling [J]. Circ Syst Video Technol IEEE Trans 17(3):298–312. doi:10.1109/TCSVT.2007.890636
Berretti S, Del Bimbo A, Vicario E (2001) Efficient matching and indexing of graph models in content-based retrieval [J]. IEEE Trans Patt Anal Mach Intell 23(10):1089–1105. doi:10.1109/34.954600
Bosch A, Zisserman A, Muoz X (2008) Scene classification using a hybrid generative/discriminative approach [J]. Patt Anal Mach Intell IEEE Trans 30(4):712–727. doi:10.1109/TPAMI.2007.70716
Boutell MR, Luo J, Brown CM (2007) Scene parsing using region-based generative models [J]. IEEE Trans Multimedia 9(1):136–146. doi:10.1109/tmm.2006.886372
Bruzzone L, Persello C (2009) A novel context-sensitive semisupervised SVM classifier robust to mislabeled training samples [J]. IEEE Trans Geosci Remote Sens 47(7):2142–2154. doi:10.1109/tgrs.2008.2011983
Caputo B, Jie L (2009) A performance evaluation of exact and approximate match kernels for object recognition [J]. Electron Lett Comp Vision Image Anal 8(3):15–26
Carbonetto P, de Freitas N, Barnard K (2004) A statistical model for general contextual object recognition[C]. Computer Vision - ECCV 2004. Lecture Notes in Computer Science Volume 3021: 350–362. doi:10.1007/978-3-540-24670-1_27
Chang E, Goh K, Sychay G et al (2003) CBSA: content-based soft annotation for multimodal image retrieval using Bayes point machines [J]. Circ Syst Video Technol IEEE Trans 13(1):26–38. doi:10.1109/TCSVT.2002.808079
Cheng H, Wang R (2010) Semantic modeling of natural scenes based on contextual Bayesian networks [J]. Patt Recog 43(12):4042–4054. doi:10.1016/j.patcog.2010.06.004
Choi MJ, Torralba A, Willsky AS (2012) A tree-based context model for object recognition [J]. Patt Anal Mach Intell IEEE Trans 34(2):240–252. doi:10.1109/TPAMI.2011.119
Duchenne O, Joulin A, Ponce J (2011) A graph-matching kernel for object categorization[C]//Proc IEEE Int Conf Comp Vis (ICCV), 1792–1799. doi:10.1109/ICCV.2011.6126445
Fei-Fei L, Perona P (2005) A Bayesian hierarchical model for learning natural scene categories [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, 2: 524–531. doi:10.1109/CVPR.2005.16
Galleguillos C, Belongie S (2010) Context based object categorization: a critical survey [J]. Comp Vision Image Underst 114(6):712–722. doi:10.1016/j.cviu.2010.02.004
Galleguillos C, Rabinovich A, Belongie S (2008) Object categorization using co-occurrence, location and appearance [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–8. doi:10.1109/CVPR.2008.4587799
Harchaoui Z, Bach F (2007) Image classification with segmentation graph kernels[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’07), 1–8. doi:10.1109/CVPR.2007.383049
Huang Y, Huang K, Wang C, et al. (2011) Exploring relations of visual codes for image classification[C]//Computer Vision and Pattern Recognition (CVPR). IEEE Conference on. IEEE, 1649–1656. doi:10.1109/CVPR.2011.5995655
Jin B, Hu W, Wang H (2012) Image classification based on pLSA fusing spatial relationships between Topics [J]. Signal Process Lett IEEE 19(3):151–154. doi:10.1109/LSP.2012.2184091
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories[C]//Computer Vision and Pattern Recognition. IEEE Comp Soc Conf IEEE 2:2169–2178. doi:10.1109/CVPR.2006.68
Liu S, Xu D, Feng S (2011) Region contextual visual words for scene categorization [J]. Expert Syst Appl 38(9):11591–11597. doi:10.1016/j.eswa.2011.03.037
Luo J, Savakis AE, Singhal A (2005) A Bayesian network-based framework for semantic image understanding [J]. Patt Recog 38(6):919–934. doi:10.1016/j.patcog.2004.11.001
Papadopoulos GT, Saathoff C, Escalante HJ et al (2011) A comparative study of object-level spatial context techniques for semantic image analysis [J]. Comp Vision Image Underst 115(9):1288–1307. doi:10.1016/j.cviu.2011.05.005
Park BG, Lee KM, Lee SU et al (2003) Recognition of partially occluded objects using probabilistic ARG (attributed relational graph)-based matching [J]. Comp Vision Image Underst 90(3):217–241. doi:10.1016/S1077-3142(03)00049-3
Qi GJ, Hua XS, Rui Y et al (2010) Image classification with kernelized spatial-context [J]. IEEE Trans Multimedia 12(4):278–287. doi:10.1109/TMM.2010.2046270
Rabinovich A, Vedaldi A, Galleguillos C, et al. (2007) Objects in context[C]//In Proc. of 11th International Conference on Computer Vision, 1–8. doi:10.1109/ICCV.2007.4408986
Serrano N, Savakis AE, Luo J (2004) Improved scene classification using efficient low-level features and semantic cues [J]. Patt Recog 37(9):1773–1784. doi:10.1016/j.patcog.2004.03.003
Shen J, Shepherd J, Ngu AHH (2005) Semantic-sensitive classification for large image libraries[C]//Multimedia Modelling Conference, 2005. MMM 2005. Proceedings of the 11th International. IEEE, 340–345. doi:10.1109/MMMC.2005.66
Singhal A, Luo J, Zhu W. Probabilistic spatial context models for scene content understanding [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003, 1: 235–241. doi:10.1109/CVPR.2003.1211359
Su Y, Jurie F (2012) Improving image classification using semantic attributes [J]. Int J Comp Vision 100(1):59–77. doi:10.1007/s11263-012-0529-4
Vailaya A, Figueiredo MAT, Jain AK et al (2001) Image classification for content-based indexing [J]. Image Proc IEEE Trans 10(1):117–130. doi:10.1109/83.892448
Vogel J, Schiele B (2007) Semantic modeling of natural scenes for content-based image retrieval [J]. Int J Comp Vision 72(2):133–157. doi:10.1007/s11263-006-8614-1
Yang J, Yu K, Gong Y, et al. (2009) Linear spatial pyramid matching using sparse coding for image classification [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, 1794–1801. doi:10.1109/CVPR.2009.5206757
Yang L, Zheng N, Yang J (2011) A unified context assessing model for object categorization [J]. Comp Vision Image Underst 115(3):310–322. doi:10.1016/j.cviu.2010.10.011
Acknowledgments
This work was partly supported by the 973 Program (2013CB329504), NSF of China (No. 61272261), NSF of Zhejiang (Y1110152), and STD of Zhejiang (2012C21002).
Author information
Authors and Affiliations
Corresponding author
Appendix: Derivation of image classification formula with Bayesian network
Appendix: Derivation of image classification formula with Bayesian network
Rights and permissions
About this article
Cite this article
Ri, CY., Yao, M. Bayesian network based semantic image classification with attributed relational graph. Multimed Tools Appl 74, 4965–4986 (2015). https://doi.org/10.1007/s11042-014-1858-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-014-1858-9