Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Similars in SciELO
Share
Computación y Sistemas
On-line version ISSN 2007-9737Print version ISSN 1405-5546
Comp. y Sist. vol.6 n.3 Ciudad de México Jan./Mar. 2003
Resumen de tesis doctoral
Methodologies for Reducing the Amount of Required Images Used for ArticledObject Recognition
Metodologías para la Reducción del Número de Imágenes Requeridas para el Reconocimiento de Objetos Articulados
Graduated: Luis Carlos Altamirano Robles
Instituto Mexicano del Petróleo, PIMAyC
Eje Central Lázaro Cárdenas 152, C.P. 07730
Del. Gustavo A. Madero, México, D. F.
Email: laltamir@imp.mx
Advisor 1: Leopoldo Altamirano
Instituto Nacional de Astrofísica, Óptica y Electrónica,
Puebla, Mexico
Email: robles@inaoep.mx
Advisor 2: Matías Alvarado Mentado
Instituto Mexicano del Petróleo
email: matiasa@cic.ipn.mx
Graduated on March 19, 2002
Abstract
The appearancebased approaches are such that any object's model is made through a set of training images describing the object's appearance. In this PhD. thesis, the usage of nonuniform sampling is introduced for building this image set. Nonuniform sampling is held by a linear interpolation technique, which is used to determine the strictly necessary images. Main results are: a significant reduction in the quantity of necessary images for the object's model, as well as more precise models than those obtained by uniform sampling. Nonuniform sampling is used in conjunction with the eigenspaces technique for object recognition, producing a more efficient hybrid technique.
Keywords: nonuniform sampling, object recognition, appearancebased model, interpolation, eigenspaces.
Resumen
Los enfoques basados en apariencia construyen el modelo de un objeto, por medio de un conjunto de imágenes de entrenamiento que describe la apariencia del objeto. En esta tesis doctoral se propone el empleo del muestreo nouniforme para generar tal conjunto de imágenes. El muestreo nouniforme es soportado mediante una técnica de interpolación, que determina cuáles son las imágenes estrictamente requeridas para construir el modelo. Los resultados principales obtenidos con esta propuesta son: una reducción significativa de la cantidad de imágenes requeridas para construir el modelo del objeto, además de una mejora en la precisión de los modelos así generados, respecto a los obtenidos con muestreo uniforme. El muestreo nouniforme es empleado junto con la técnica de espacios fundamentales (eigenspaces) para realizar el reconocimiento del objeto, obteniéndose una técnica híbrida más eficiente.
Palabras Clave: nonuniform sampling, object recognition, appearancebased model, interpolation, eigenspaces.
DESCARGAR ARTÍCULO EN FORMATO PDF
Acknowledgments
This research was sponsored in part by CONACyT under Ref. 131991 A. L.C. Altamirano was supported by CONACyT graduate scholarship No. 89635. The author would like to thank Dr. Matías Alvarado from Instituto Mexicano del Petróleo (PIMAyC), for reviewing and correcting a preliminary version of this work.
References
L.C. AltamiranoRobles. "Metodologías para la reducción del número de imágenes requeridas, para el reconocimiento de objetos articulados". Dissertation, PhD. Thesis, Centro de Investigación en Computación, Instituto Politécnico Nacional, México, D.F., March, 2002. [ Links ]
L.C. Altamirano, L. Altamirano, and M. Alvarado. "Generation of Nparametric appearancebased models through nonuniform sampling". Submitted to Pattern Recognition Letters, The Netherlands, 2002. [ Links ]
L.C. Altamirano, L. Altamirano, and M. Alvarado. "NonUniform Sampling For Improved AppearanceBased Models". Pattern Recognition Letters, Vol. 24, Issue 13, pp. 521535, The Netherlands, January 2003. [ Links ]
P.N. Belhumeur and D.J. Kriegman. "What is the Set of Images of an Object Under All Possible Ilumination Conditions?". International Journal of Computer Vision, Vol. no. 28, Issue No. 3, 245260, 1998. [ Links ]
T.F. Cootes, G.V. Wheeler, K.N. Walker and C.J. Taylor. "CoupledView Active Appearance Models". The Eleventh British Machine Vision Conference, University of Bristol, September 2000. [ Links ]
R. Epstein, P. Hallinan, and A. Yuille. "5±2 Eigenimages suffice: An empirical investigation of lowdimensional lighting models". In proceedings of IEEE Workshop on physicsbased modeling in computer vision, 1995. [ Links ]
J.J. Koenderink and A.J. Van Doorn. "The internal representation of solid shape with respect to vision". Biological Cybernetics, Vol. 32, 1979. [ Links ]
B. Moghaddam and A. Pentland. "Probabilistic visual learning for object representation", in Early Visual Learning, Edited by Shree K. Nayar and Tomaso Poggio, New York Oxford, Oxford University Press, 1996. [ Links ]
F. Mokhtarian and S. Abbasi. "Automatic Selection of Optimal Views in Multiview Object Recognition". The Eleventh British Machine Vision Conference, University of Bristol, September 2000. [ Links ]
H. Murase and S.K. Nayar. "Visual learning and recognition of 3D objects from appearance". International Journal of Computer Vision, Vol. 14, No. 1, 524, January 1995. [ Links ]
S.K. Nayar, H. Murase and S. Nene. "Parametric Appearance Representation". In Early Visual Learning, Edited by Shree K. Nayar and Tomaso Poggio, New York Oxford, Oxford University Press, 1996. Workshop, 11971205, 1997. [ Links ]
R.C. Nelson and A. Selinger. "Experiments on (Intelligent) Brute Force Methods for AppearanceBased Object Recognition". DARPA Image Understanding. [ Links ]
K. Ohba and K. Ikeuchi. "Recognition of the Multi Specularity Objects using the EigenWindow". Proceedings of International Conference on Pattern Recongnition, August 1996. [ Links ]
J. Pauli, M. Benkwitz and G. Sommer. "RBF Networks AppearanceBased Object Detection". Proceedings of ICANN, Paris, Volume 1, pp. 359364, 1995. [ Links ]
T. Poggio and D. Beymer. "Regularization Networks for Visual Learning". In Early Visual Learning, Edited by Shree K. Nayar and Tomaso Poggio, New York Oxford, Oxford University Press, 1996. [ Links ]
A. Pope and D. Lowe. "Learning Probabilistic Appearance Models for Object Recognition". In Early Visual Learning, Edited by Shree K. Nayar and Tomaso Poggio, New York Oxford, Oxford University Press, 1996. [ Links ]
B. Schiele and J.L. Crowley. "Recognition without Correspondence using Multidimensional Receptive Field Histograms". International Journal of Computer Vision 36(1), 3150, 2000. [ Links ]
L.G. Shapiro and M.S. Costa. "AppearanceBased 3D Object Recognition". Object Representation in Computer Vision, Vol. I, in Proceedings of International NSFARPA Workshop, New York City, NY, USA, Dec. 1994. 5164. [ Links ]
M.R. Stevens and J.R. Beveridge. "Integrating graphics and vision for object recognition". Kluwer Academic Publishers, 2000. [ Links ]
M. Turk and A. Pentland. "Eigenfaces for Recognition". J. Cognitive Neuroscience, Vol. 3, no. 1, 7186, 1991. [ Links ]