Modelling Objects Using Kernel Principal Component Analysis

Rajkumari Bidyalakshmi Devi, Romesh Laishram, Yumnam Jayanta Singh

Abstract


Object detection is a technologically challenging and practically useful field of computer vision.The success of object detection relies on modelling of an object class. Statistical shape modelling is one of the popular method. Object modelling starts with asset of examples shapes (the training set), and learn from this the pattern of variability of the shape of the class of objects for which the training set can be considered a representative sample. Modelling can considered as the process of modelling the distribution of the training points in shape space. In this paper we present Kernel principal component analysis (KPCA) based active shape models (ASM) for learning the intra –class deformation modes of an object. KPCA is the non-linear dimensionality reduction method. The comparison on performance and space of KPCA and principal component analysis (PCA) are shown

Keywords: Object model, KPCA, PCA, ASM.

Cite as: Rajkumari Bidyalakshmi Devi, Romesh Laishram, Y.J. Singh, “Modelling Objects Using Kernel
Principal Component Analysis†ADBU J.Engg.Tech.,2(1)(2015) 0021102(5pp)

Full Text:

PDF

References


T. F. Cootes and C. J. Taylor. Statistical models of appearance for computer vision.online document,Postscript: www.isbe.man.ac.uk/Ëœbim/Models/app model.ps.gz.

R.Davies, C.Twining, C.Taylor, “Statistical models of shape:optimization and evaluationâ€, Springer, First Edition, ISBN: 978-1-84800-137-4 ,2008, DOI: 10.1007/978-1-84800-138-1.

Vittorio Ferrari- Federic Jurie,Cordelia Schmid,2009,â€From Image to shape models for object

Detection†.,Int J Comput Vis (2010) 87: 284–303DOI 10.1007/s11263-009-0270-9

Cootes, T. F. Taylor, C. J. Cooper D. H. Graham J.,Active shape models, their training and application.Computer Vision and Image understanding, 61(1):38,1995.

T. F. Cootes, A. Hill, and C. J. Taylor., “ The use of Active Shape Models for locating structure in medical imagesâ€, Image and Vision Computing, 12(6):355–366, 1994.

I. T. Joliffe. “Principal Component Analysisâ€, Springer Series in Statistics. Springer-Verlag, New York, 1986.

Schlkopf, Bernhard, Smola, Alexander, and Mller,Klaus-Robert. “Nonlinear component analysis as a kernel eigenvalue problemâ€, 1996.

Scholkopf, Bernhard, Smola, Alexander, and Mller, Klaus-Robert. “Kernel principal component analysisâ€, In Advances in Kernel Methods-Support Vector Learning, pp. 327{352. MIT Press, 1999.

S. Mika, B. Sch¨olkopf, A. Smola, K.-R. M¨uller, M. Scholz, and G. R¨atsch. Kernel PCA and de-noising in feature spaces. In M. S. Kearns, S. A. Solla, and D. A. Cohn, editors, Advances in Neural Information Processing Systems, volume 11, pages 536– 542. MIT Press, Cambridge, MA, 1999.

S. Romdhani, S. Gong, and A. Psarrou. A multi-view nonlinear active shape model using kernel PCA. In T. Pridmore and D. Elliman, editors, Proceedings of the 10th British Machine Vision Conference (BMVC99), pages 483–492.BMVA Press, 1999.

V Ferrari, T Tuytelaars, L Van Gool, "Object detection by contour segment networks." Computer Vision– ECCV 2006. Springer Berlin Heidelberg, 2006. 14-28.

S. Belongie, J. Malik, J. Puzicha, “Shape Matching and Object Recognition Using Shape Contextsâ€, PAMI, 24:4, 2002.

V.Ferrari, L. Fevrier, F. Jurie, C. Schmid, Groups of adjacent contour segments for object detection. Pattern Analysis and Machine Intelligence, 30, 36–51, 2008.

V Ferrari, L Fevrier, F Jurie, 'Pattern Analysis and Machine Intelligence', IEEE Transactions on 30.1, 36- 51, 2008

J. Shotton, A. Blake, R. Cipolla, Contour-based learning for object detection, ICCV, 2005

N. Dalal, , B. Triggs, Histograms of oriented gradients for human detection, CVPR, 2005

A. Berg, T. Berg, T., & J. Malik. Shape matching and object recognition using low distortion correspondence, CVPR, 2005

M. Leordeanu, M. Hebert, R. Sukthankar, Beyond local appearance: Category recognition from pairwise interactions of simple features, CVPR, 2005


Refbacks

  • There are currently no refbacks.


------------------------------------------------------------------------------------------------------------------------

The ADBU Journal of Engineering Technology (AJET)" ISSN:2348-7305

This journal is published under the terms of the Creative Commons Attribution (CC-BY) (http://creativecommons.org/licenses/)

Number of Visitors to this Journal: