Multi-Scale Semantic Model for Unsupervised Object Segmentation

Abstract:

It is difficult to segment instances of object classes accurately unsupervised in images, because of the complexity of structures, inter-class differences, background interference and so on. A multi-scale semantic model method is proposed to overcome the disadvantages existing in most of the relative methods. This method uses generative model to deal with the objects obtained by multi-scale segmentations instead of whole image, and calculates kinds of visual features to mine the topic information of every object. In the segmentation process, a semantic correlative function of every segment block based on KL divergence is built up and minimized to select the object correct regions. Experimental results demonstrate the effectiveness of the proposed method.

• Periodical: Advanced Materials Research (Volumes 532-533)
• Pages: 859-864
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.532-533.859
• Online since: June 2012
• Authors: Yu Li, Xiang Juan Li, Ya Sen Zhang, Xian Sun, Hong Qi Wang
• Keywords: Image Process, LDA, Multi-Scale, Object Segmentation, Semantic Model

References

[1] J. Vogel and B. Schiele. Semantic modeling of natural scenes for content-based image retrieval. International Journal of Computer Vision, Vol. 2 (2007), pp.133-157.

DOI: 10.1007/s11263-006-8614-1

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

[3] L. Fei-Fei and P. Perona. A bayesian hierarchical model for learning natural scene categories. Proc. of IEEE Computer Vision and Pattern Recognition (2005), pp.524-531.

DOI: 10.1109/cvpr.2005.16

[4] J. Sivic, B. Russell, A. Efros, A. Zisserman, and W. Freeman. Discovering object categories in image collections. In Proc. of the 10th IEEE International Conference on Computer Vision, Beijing, China (2005), pp.370-377.

DOI: 10.1109/iccv.2005.77

[5] Erik B. Sudderth, Antonio Torralba, William T. Freeman and Alan S. Willsky. Describing visual scenes using transformed objects and parts. International Journal of Computer Vision, (2008).

DOI: 10.1007/s11263-007-0069-5

[6] B. Russell, A. Efros, J. Sivic, W. Freeman, and A. Zisserman. Using multiple segmentations to discover objects and their Extent in image collections. CVPR, (2006).

DOI: 10.1109/cvpr.2006.326

[7] J. Shi and J. Malik. Normalized Cuts and Image Segmentation. TPAMI, Vol. 8 (2000), pp.888-905.

[8] Mikolajczyk K and Schmid C. An affine invariant interest point detector. In Proceedings of the 8th International Conference on Computer Vision, Vancouver, Canada (2002).

[9] Matas J, Chum O, Urban M and Pajdla T. Robust wide baseline stereo from maximally stable extremal regions, BMVC (2002).

DOI: 10.5244/c.16.36

[10] Lowe D G. Object recognition from local scale-invariant features. In International Conference on Computer Vision, Corfu, Greece (1999).

DOI: 10.1109/iccv.1999.790410

[11] D. Blei and A. Ng, M. Jordan. Latent dirichlet allocation. Journal of Machine Learning Research, Vol. 3 (2003), pp.993-1022.

[12] Cao Juan, Xia Tian, Jin-Tao, et al. A density-based method for adaptive LDA model selection. Neurocomputing, Vol. 7-9 (2009), pp.1775-1781.

DOI: 10.1016/j.neucom.2008.06.011