Special Issue on Computational Intelligence in Signal and Image Processing; Guest Editors: Yen-Wei Chen and Vasile PaladeNo Access

A NON-PARAMETRIC TRAINABLE OBJECT-DETECTION MODEL USING A CONCEPT OF RETINOTOPIC SAMPLING

HIROTAKA NIITSUMA

HIROTAKA NIITSUMA

Kwansei Gakuin University, 2-1 Gakuen Sanda 669-1337, Japan

Search for more papers by this author

https://doi.org/10.1142/S1469026804001185Cited by:0 (Source: Crossref)

Abstract

A retina has a space-variant sampling mechanism and an orientation-sensitive mechanism. The space-variant sampling mechanism of the retina is called Retinotopic Sampling (RS). With these mechanisms, the object-detection is formulated as finding an appropriate coordinate transformation from a coordinate system on the input image to the retina. The appropriate coordinate transformation is found using maximum likelihood method. By using the model based on RS, we formulate a kernel function as an analytical function of the information on the input image, the position and the size of the object in the input image. Then the object-detection is realised as a gradient decent method for a discriminant function trained by Support Vector Machine (SVM). This detection mechanism realises faster detection than exploring a visual scene in raster-like fashion. The discriminant function outperforms results of SVMs using a kernel function using intensities of all pixels (based on independently published results), in face detection experiments over test images in the MIT-CBCL face database.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

M. Alvira and R. Rifkin, An empirical comparison of snow and SVMs for face detection, A.I. Memo 2001-004, Center for Biological and Computational Learning (MIT, Cambridge, MA, 2001) . Google Scholar
S. Avidan, Support vector tracking, CVPR, 2001 . Google Scholar
R. Collobert and S. Bengio, JMLR (2001). Google Scholar
T. G. Dietterich and X. Wang, NIPS (2001). Google Scholar
B. Heisele, T. Poggio and M. Pontil, Face detection in still gray images, A.I. Memo 1687, Center for Biological and Computational Learning (MIT, Cambridge, MA, 2000) . Google Scholar
L. Itti and C. Koch, Syst. J. Electron. Imaging (2001). Google Scholar
T. S. Jaakkola and D. Haussler, NIPS 11, 487 (1999). Google Scholar
M.C. for Biological and C. Learning, CBCL Car database, http://www.ai.mit.edu/projects/cbcl/ . Google Scholar
M.C. for Biological and C. Learning, CBCL face database, http://www.ai.mit.edu/projects/cbcl/ . Google Scholar
H. Niitsuma and S. Ishii , Learning of minimax strategy by a support vector machine , ICONIP ( 2000 ) . Google Scholar
C. Papageorgiou and T. Poggio , A pattern classification approach to dynamical object detection , ICCV ( 1999 ) . Google Scholar
T. Provost , F. Fawcett and R. Kohavi , The case against accuracy estimation for comparing induction algorithms , IMLC ( 1998 ) . Google Scholar
H. Rowley , S. Baluja and T. Kanade , Rotation invariant neural network-based face detection , Proc. IEEE Conf. Gomput. Vision Pattern Recognition . Google Scholar
F. Smeraldi, Attention-driven pattern recognition, Ph.D. thesis, 2000 . Google Scholar
F. Smeraldi and J. Bigun, Pattern, Recognition Lett. (2002). Google Scholar
H. Tao, H. S. Sawhney and R. Kumar, IEEE Trans. Pattern Anal. Mach. Intell. (2002). Google Scholar
J. J. Verbeek, N. Vlassis and B. Krose, Efficient greedy learning of Gaussian mixture models, Neural Gomput., to appear . Google Scholar