Classification and pose estimation of objects using nonlinear features

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 3390, Issue , 1998, Pages 12-23

  Talukder, Ashit ^a   Casasent, David ^a  

^a CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

Active vision; Classification; Discrimination (nonlinear); Feature extraction; Neural networks; Pose estimation; Principal component analysis; Representation

Indexed keywords

ARTIFICIAL INTELLIGENCE; CLASSIFICATION (OF INFORMATION); COMPUTER AIDED DESIGN; EXTRACTION; FEATURE EXTRACTION; NEURAL NETWORKS; NONLINEAR ANALYSIS; SPACE FLIGHT;

ACTIVE VISION; DISCRIMINATION (NONLINEAR); FEATURE EXTRACTION METHODS; NEURAL NETWORK CLASSIFIER; NONLINEAR FEATURE EXTRACTION METHOD; NONLINEAR NEURAL NETWORKS; POSE ESTIMATION; REPRESENTATION;

PRINCIPAL COMPONENT ANALYSIS;

EID: 0003966348     PISSN: 0277786X     EISSN: 1996756X     Source Type: Conference Proceeding    
DOI: 10.1117/12.304801     Document Type: Conference Paper

References (27)

1. R. Bajcsy. Active perception. IEEE Proceedings, 76(8):996-1006, 1988.
2. J. Y. Aloimonos, I. Weiss, and A. Bandopadhay. Active vision. Intl. Journal of Computer Vision, pages 333-356, 1987.
3. K. Sengupta and J. Ohya. Pose estimation of human body part using multiple cameras. In Proc. Fifth IEEE International Workshop on Robot and Human Communication, pages 146-151. Nov. 1996.
4. S. Yamane, M. Izumi, and K. Fukunaga. A method of model-based pose estimation. Transactions of the Institute of Electronics, Information and Communication Engineers D-Il, J79DII (2):165-173, 1996.
5. P. Wlczek, A. Maccato, and R. J. P De Figueiredo. Pose estimation of three-dimensional objects from single camera images. Digital Signal Processing. 5(3):176-183, 1995.
6. R. M, Hoogeveen and M. J. Korsten. The use of silhouettes in 3d scene recognition and pose estimation. In Proc. Ninth Conference on Theory and Applications of Image Analysis II, pages 183 196, Jun. 1995.
7. J. Dunker, G. Hartmann, and M. Stohr. Single view recognition and pose estimation of 3d objects using sets of prototypical views and spatially tolerant contour representations. In Proc. 13'th Int. Conf. Pattern Recognition, volume 4, pages 25-29, Aug. 1996.
8. A. Khotanzad and J. J. Liou. Recognition and pose estimation of unoccluded three-dimensional objects from a twodimensional perspective view by banks of neural networks. IEEE Trans. Neural Networks, 7(4):291-303, 1996.
9. C. B. Madsen. A comparative study of the robustness of two pose estimation techniques. Machine Vision and Applications, 9 (5-6):291-303, 1997.
10. T. Darrell, B. Moghaddam, and A. P. Pentland. Active face tracking and pose estimation in an interactive room. In Proc. IEEE Conf. on Comp. Vision and Pattern Recognition, pages 67-72, Aug. 1996.
11. H. Hotelling. Analysis of a complex of statistical variables into principal components. J. Educ. Psychology, 24:417-441 and 498-520, 1933.
12. D. L. Swets and J. J. Weng. Using discriminant eigenfeatures for image retrieval. IEEE Trans. PAMI, 18(8):831-836, Aug. 1996.
13. K. Fukunaga and W. L. G. Koontz. Applications of the Karhunen-Loeve expansion to feature selection and ordering. IEEE Trans. Comp., C-19:917-923, 1970.
14. R. A. Fisher. Contributions to Mathematical Statistics. John Wiley, New York, 1950.
15. G. Taylor and S. Coombes. Learning higher order correlations. Neural Networks, 6:423-427, 1993.
16. J. Karhunen and J. Joutsensalo. Representation and separation of signals using nonlinear PCA type learning. Neural Networks, 7(1):113-127, 1994.
17. G. Burel. Blind separation of sources: A nonlinear neural algorithm. Neural Networks, 5:937-947, 1992.
18. G. F. Ramponi, G. L. Sicuranza, and W. Ukovich. A computational method for design of 2-D nonlinear Volterra filters. IEEE Trans. on Circuits and Systems, 35(9):1095-1102, Sept. 1988.
19. J. Karhunen and J. Joutsensalo. Generalizations of principal component analysis, optimization problems, and neural networks. Neural Networks, 8(4):549-562, 1995.
20. W. S. Softky and D. M. Kammen. Correlations in high dimensional or asymmetric data sets: Hebbian neuronal processing. Neural Networks, 4(3):337-348, Nov. 1991.
21. E. Oja. A simplified neuron model as a principal component analyzer. Journal of Mathematical Biology, 15:267-273, 1982.
22. A. Talukder and D. Casasent. A general methodology for simultaneous representation and discrimination of multiple object classes. Optical Engineering, Special Issue on Advanced Recognition Techniques, March 1998.
23. P. Gader. Template generation for pattern classification. In Proc. SPIE: Image algebra and Morphological Image Processing III, volume 1769, pages 72-81, Jul. 1992.
24. Malcolm Heywood and Peter Noakes. A framework for improved training of Sigma-Pi networks. IEEE Transactions on Neural Networks, 6(4):893-903, July 1995.
25. D. Casasent and L. Neiberg. Classifier and shift-invariant ATR neural networks. Neural Networks, 8 (7/8):1117-1129, 1995.
26. S. A. Nene, S. K. Nayar, and H. Murase. Columbia image object library (COIL-20). Technical Report CUCS-006-96. Dept. of Computer Science, Columbia University, New York, NY 10027, 1996.
27. W. C. Regli and D. S. Nau. Recognition of volumetric features from CAD models: Problem formalization and algorithms. In Technical Report: University of Maryland, number 93-41, 1993.