IMPROVING FEATURE LEVEL LIKELIHOODS USING CLOUD FEATURES

Heydar Maboudi Afkham, Stefan Carlsson, Josephine Sullivan

2012

Abstract

The performance of many computer vision methods depends on the quality of the local features extracted from the images. For most methods the local features are extracted independently of the task and they remain constant through the whole process. To make features more dynamic and give models a choice in the features they can use, this work introduces a set of intermediate features referred as cloud features. These features take advantage of part-based models at the feature level by combining each extracted local feature with its close by local feature creating a cloud of different representations for each local features. These representations capture the local variations around the local feature. At classification time, the best possible representation is pulled out of the cloud and used in the calculations. This selection is done based on several latent variables encoded within the cloud features. The goal of this paper is to test how the cloud features can improve the feature level likelihoods. The focus of the experiments of this paper is on feature level inference and showing how replacing single features with equivalent cloud features improves the likelihoods obtained from them. The experiments of this paper are conducted on several classes of MSRCv1 dataset.

References

  1. Bosch, A., Zisserman, A., and Munoz, X. (2007). Representing shape with a spatial pyramid kernel. In CIVR, pages 401-408. Association for Computing Machinery.
  2. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In CVPR, pages 886- 893.
  3. Felzenszwalb, P., Girshick, R., Mcallester, D., and Ramanan, D. (2009). Object detection with discriminatively trained part based models. Pattern Analysis and Machine Intelligence, IEEE Transactions on.
  4. Felzenszwalb, P. F., Girshick, R. B., McAllester, D., and Ramanan, D. (2010). Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32:1627-1645.
  5. Felzenszwalb, P. F. and Huttenlocher, D. P. (2005). Pictorial structures for object recognition. IJCV, 61:55-79.
  6. Kumar, S. and Hebert, M. (2006). Discriminative random fields. IJCV, 68:179-201.
  7. Laptev, I. (2006). Improvements of object detection using boosted histograms. In BMVC, pages 949-958.
  8. Ling, H. and Soatto, S. (2007). Proximity distribution kernels for geometric context in category recognition. In ICCV.
  9. Liu, D., Hua, G., Viola, P., and Chen, T. (2008). Integrated feature selection and higher-order spatial feature extraction for object categorization. CVPR, 0:1-8.
  10. Lowe, D. G. (2003). Distinctive image features from scaleinvariant keypoints.
  11. Morioka, N. and Satoh, S. (2010). Building compact local pairwise codebook with joint feature space clustering. In ECCV, page 14, Crete, Greece.
  12. Savarese, S., Winn, J., and Criminisi, A. (2006). Discriminative object class models of appearance and shape by correlatons. CVPR, 2:2033-2040.
  13. Varma, M. and Zisserman, A. (2002). Classifying images of materials: Achieving viewpoint and illumination independence. In ECCV, pages 255-271, London, UK. Springer-Verlag.
  14. Varma, M. and Zisserman, A. (2003). Texture classification: Are filter banks necessary. In CVPR.
  15. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. CVPR, 1:511.
  16. Winn, J., Criminisi, A., and Minka, T. (2005). Object categorization by learned universal visual dictionary. In ICCV, ICCV 7805, pages 1800-1807, Washington, DC, USA. IEEE Computer Society.
Download


Paper Citation


in Harvard Style

Maboudi Afkham H., Carlsson S. and Sullivan J. (2012). IMPROVING FEATURE LEVEL LIKELIHOODS USING CLOUD FEATURES . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-8425-99-7, pages 431-437. DOI: 10.5220/0003777904310437


in Bibtex Style

@conference{icpram12,
author={Heydar Maboudi Afkham and Stefan Carlsson and Josephine Sullivan},
title={IMPROVING FEATURE LEVEL LIKELIHOODS USING CLOUD FEATURES},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2012},
pages={431-437},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003777904310437},
isbn={978-989-8425-99-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - IMPROVING FEATURE LEVEL LIKELIHOODS USING CLOUD FEATURES
SN - 978-989-8425-99-7
AU - Maboudi Afkham H.
AU - Carlsson S.
AU - Sullivan J.
PY - 2012
SP - 431
EP - 437
DO - 10.5220/0003777904310437