Beyond Bag-of-Words: combining generative and discriminative models for scene categorization
This paper proposes an efficient framework for scene categorization by combining generative model and discriminative model. A state-of-the-art approach for scene categorization is the Bag-of-Words (BoW) framework. However, there exist many categories in scenes. Generally when a new category is considered, the codebook in BoW framework needs to be re-generated, which will involve exhaustive computation. In view of this, this paper tries to address the issue by designing a new framework with good scalability. When an additional category is considered, much lower computational cost is needed while the resulting image signatures are still discriminative. The image signatures for training discriminative model are carefully designed based on the generative model. The soft relevance value of the extracted image signatures are estimated by image signature space modeling and are incorporated in Fuzzy Support Vector Machine (FSVM). The effectiveness of the proposed method is validated on UIUC Scene-15 dataset and NTU-25 dataset, and it is shown to outperform other state-of-the-art approaches for scene categorization.
KeywordsScene categorization Bag-of-Words Generative model Discriminative model Scalability
This work is supported by Agency for Science, Technology and Research (A*STAR), Singapore under SERC Grant 062 130 0055. Thank Dr. J. C. van Gemert for kindly providing the source code of UNC in . Thank the anonymous reviewers for providing the valuable suggestions that significantly improve the quality of the paper.
- 1.Boiman O, Shechtman E, Irani M (2008) In defense of nearest-neighbor based image classification. In: IEEE conference on computer vision and pattern recognition, pp 1–8Google Scholar
- 3.Csurka G, Dance C, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, European conference on computer visionGoogle Scholar
- 5.Dorko G, Schmid C (2005) Object class recognition using discriminative local features. In: INRIA Technical Report, RR-5497Google Scholar
- 6.Fifteen Scene Categories, http://www-cvr.ai.uiuc.edu/ponce_grp/data
- 7.Jiang, Y-G, Ngo C-W, Yang J (2007) Towards optimal bag-of-features for object categorization and semantic video retrieval. In: ACM international conference on image and video retrievalGoogle Scholar
- 9.Li Z, Yap K-H, Chen X (2011) Beyond bags of words: combining generative and discriminative models for natural scene categorization. In: International conference on acoustics, speech and signal processing, pp 965–968Google Scholar
- 10.Nowak E, Jurie F, Triggs B (2006) Sampling strategies for bag-of-features image classification. In: European conference on computer vision, pp 490–503Google Scholar
- 11.Sivic J, Zisserman A (2003) Video google: a text retrieval approach to object matching in videos. In: Proc. int. conf. comput. vis., vol 2, pp 1470–1477Google Scholar
- 14.Szummer M, Picard RW (1998) Indoor-outdoor image classification. In: IEEE international workshop on content-based access of image and video database, pp 42–51Google Scholar
- 17.Yu Z, Wong HS (2006) FEMA: A fast expectation maximization algorithm based on grid and PCA. In: IEEE international conference on multimedia & expo, pp 1913–1916Google Scholar