SCENE CATEGORIZATION USING LOW-LEVEL VISUAL FEATURES

Ioannis Pratikakis, Basilios Gatos, Stelios C.A. Thomopoulos

Abstract

In this paper, we have built two binary classifiers for indoor/outdoor and city/landscape categories, respectively. The proposed classifiers consist of robust visual feature extraction that feeds a support vector classification. In the case of indoor/outdoor classification, we combine color and texture information using the first three moments of RGB color space components and the low order statistics of the energy wavelet coefficients from a two-level wavelet pyramid. In the case of city/landscape classification, we combine the first three moments of L*a*b color space components and structural information (line segment orientation). Experimental results show that a high classification accuracy is achieved.

References

  1. Canny, J., 1986. A Computational Approach to Edge Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, No. 6, pp. 679- 698.
  2. Cortes C., and Vapnik, V., 1995. Support-vector network, Machine Learning, vol. 20, pp. 273-297.
  3. Daubechies, I., 1988. Orthonormal bases of compactly supported wavelets, Communications on Pure and Applied Mathematics, vol. XLI, no. 41, pp. 909-996.
  4. Microsoft Research Cambridge (MRC) Object Recognition Image Database 1.0, http://research.microsoft.com/research/downloads/
  5. MPEG-7 VCE-2 Dataset, http://mpeg.nist.gov
  6. Lim, J-H., and Jin, J.S., 2005. Combining intra-image and inter-class semantics for consumer image retrieval, Pattern Recognition, vol. 38, pp. 847-864.
  7. Luo, J., and Savakis, A., 2001. Indoor vs. Outdoor classification of consumer photographs using low-level and semantic features, In Proceedings of International Conference of Image Processing (ICIP), vol. II, pp. 745-748.
  8. Payne, A., and Singh, S., 2005, Indoor vs. outdoor scene classification in digital photographs, Pattern Recognition, vol. 38, pp. 1533-1545.
  9. Rosin, P.,L., and West, G.A.W., 1995. Nonparametric segmentation of curves into various representations, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, No. 12, pp. 1140-1153.
  10. Sebe, N., and Lew, M.S., 2003, Comparing salient point detectors, Pattern Recognition Letters, vol. 24, pp. 89- 96.
  11. Stauder, J., Sirot, J., Le Borgne, H., Cooke E., and O'Connor, N.E., 2004. Relating visual and semantic image descriptors, In Proc. of European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology,pp. 221-228, London, UK, November 25-26.
  12. Serrano, N., Savakis, A., and Luo, J., 2004. Improved scene classification using efficient low-level features and semantic cues, Pattern Recognition, vol. 37, pp. 1773-1784.
  13. Szummer, M., and Picard, R., 1998. Indoor-outdoor image classification, In Proc. of Int. Workshop on Contentbased access of image and video databases, pp. 42-51.
  14. Theodoridis, S., and Koutroumbas, K., 1997. Pattern Recognition, Academic Press.
  15. Unser, M., 1995. Texture Classification and Segmentation Using Wavelet Frames, IEEE Trans. Image Processing, vol. 4, no. 11, pp. 1549-1560.
  16. Vailaya, A., Figueiredo, M.A.T., Jain, A.K, and Zhang, HJ., 2001, Image classification for content-based indexing, IEEE Transactions on Image Processing, vol. 10, No. 1, pp. 117-130.
  17. Vapnik, V., 1998. Statistical Learning Theory, Wiley, New York.
  18. Wyszecki, G. and Stiles, W., 1982. Color Science: Concepts and Methods, Quantitative Data and Formulae, second ed. Wiley.
Download


Paper Citation


in Harvard Style

Pratikakis I., Gatos B. and C.A. Thomopoulos S. (2006). SCENE CATEGORIZATION USING LOW-LEVEL VISUAL FEATURES . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 155-160. DOI: 10.5220/0001374901550160


in Bibtex Style

@conference{visapp06,
author={Ioannis Pratikakis and Basilios Gatos and Stelios C.A. Thomopoulos},
title={SCENE CATEGORIZATION USING LOW-LEVEL VISUAL FEATURES},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={155-160},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001374901550160},
isbn={972-8865-40-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - SCENE CATEGORIZATION USING LOW-LEVEL VISUAL FEATURES
SN - 972-8865-40-6
AU - Pratikakis I.
AU - Gatos B.
AU - C.A. Thomopoulos S.
PY - 2006
SP - 155
EP - 160
DO - 10.5220/0001374901550160