Abstract
The paper proposes an extension of support vector machines (SVMs) for recognizing position and size of objects in digital images. The discriminant function is given as an analytical function of the object position and size. Using Fisher kernel, a concept of Retinotopical Sampling(RS) is introduced to SVMs.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alvira, M., Rifkin, R.: An empirical comparison of snow and svms for face detection. In: AI Memo 2001-004 January 2001,CBCL Memo 193 (2001)
Avidan, S.: Support vector tracking. In: CVPR (2001)
Carlson, A.J., Cumby, C.M., Rosen, J.L., Roth, D.: Snow user’s guide. Technical report, UIUC (1999)
Collobert, R., Bengio, S.: SVMTorch: Support Vector Machines for Large-Scale Regression Problems. JMLR (2001)
Itti, L., Koch, C.: Feature combination strategies for saliency-based visual attention. Systems Journal of Electronic Imaging (2001)
Jaakkola, T., Haussler, D.: Exploiting generative models in discrimative classifiers. In: NIPS
Papageorgiou, C., Poggio, T.: A pattern classification approach to dynamical object detection. In: ICCV (1999)
Provost, T., Fawcett, F., Kohavi, R.: The case against accuracy estimation for comparing induction algorithms. In: IMLC (1998)
Smeraldi, F., Bigun, J.: Retinal vision applied to facial features detection and face authentication. Pattern Recognition Letters (2002)
Tao, H., Sawhney, H., Kumar, R.: Object tracking with bayesian estimation of dynamic layer representations. IEEE Tpami (2002)
Verbeek, J., Vlassis, N., Krose, B.: Efficient greedy learning of gaussian mixture models. Neural Computation (page to appear)
Yang, D., Roth, M.H., Ahuja, N.: A snow-based face detector. In: NIPS (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Niitsuma, H. (2003). A Trainable Object-Detection Method Using Equivalent Retinotopical Sampling and Fisher Kernel. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2774. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45226-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-540-45226-3_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40804-8
Online ISBN: 978-3-540-45226-3
eBook Packages: Springer Book Archive