Advertisement

Unsupervised Feature Selection and Category Formation for Generic Object Recognition

  • Hirokazu Madokoro
  • Masahiro Tsukada
  • Kazuhito Sato
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6854)

Abstract

This paper presents an unsupervised method for selection of feature points and object category formation without previous setting of the number of categories. For unsupervised object category formation, this method has the following features: selection of target feature points using One Class-SVMs (OC-SVMs), generation of visual words using Self-Organizing Maps (SOMs), formation of labels using Adaptive Resonance Theory-2 (ART-2), and creation and classification of categories for visualizing spatial relations between them using Counter Propagation Networks (CPNs) . Classification results of static images using a Caltech-256 object category dataset demonstrate that our method can visualize spatial relations of categories while maintaining time-series characteristics. Moreover, we emphasize the effectiveness of our method for category formation of appearance changes of objects.

Keywords

Feature Point Visual Word Recognition Accuracy Category Formation Sift Feature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Carpenter, G.A., Grossberg, S.: Art 2: Stable self-organization of pattern recognition codes for analog input patterns. Applied Optics 26Google Scholar
  2. 2.
    Chen, Y., Zhu, L., Yuille, A., Zhang, H.Google Scholar
  3. 3.
    Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Proc. European Conf. Computer VisionGoogle Scholar
  4. 4.
    Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset, California Institute of Technology Technical ReportGoogle Scholar
  5. 5.
    Hecht-Nielsen, R.: Counterpropagation networks. Applied Optics 26(23), 4979–4984 (1987)CrossRefGoogle Scholar
  6. 6.
    Kohonen, T.: Self-organized formation of topologically correct feature maps. Biological Cybernetics 43(1), 59–69 (1982)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Scholkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high dimensional distribution. Neural Computation 13, 1443–1471 (2001)CrossRefMATHGoogle Scholar
  8. 8.
    Sivic, J., Russell, B.C., Zisserman, A., Efros, A.A., Freeman, W.T.: Discovering objects and their localization in images. In: Proc. Conf. Computer VisionGoogle Scholar
  9. 9.
    Terashima, M., Shiratani, F., Yamamoto, K.: Unsupervised cluster segmentation method using data density histogram on self-organizing feature map. Journal of the Institute of Electronics, Information, and Communication Engineers (D–II), 1280–1290 (1996)Google Scholar
  10. 10.
    Todorovic, S., Ahuja, N.: Unsupervised category, modeling, recognition, and segmentation in images. IEEE Trans. Pattern Analysis and Machine Intelligence 30(12), 2158–2174 (2008)CrossRefGoogle Scholar
  11. 11.
    Yanai, K.: The current state and future directions on generic object recognition. Journal of Information Processing: The Computer Vision and Image Media 48Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Hirokazu Madokoro
    • 1
  • Masahiro Tsukada
    • 1
  • Kazuhito Sato
    • 1
  1. 1.Department of Machine Intelligence and Systems EngineeringAkita Prefectural UniversityYurihonjo CityJapan

Personalised recommendations