This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
PERFORM: A Fast Object Recognition Method Using Intersection of Projection Error Regions
May 1997 (vol. 19 no. 5)
pp. 499-506
ASCII Text
x 
 
Bharath R. Modayur, Linda G. Shapiro, "PERFORM: A Fast Object Recognition Method Using Intersection of Projection Error Regions," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 5, pp. 499-506, May, 1997.
 
 
BibTex
x
 
@article{ 10.1109/34.589210,
author = {Bharath R. Modayur and Linda G. Shapiro},
title = {PERFORM: A Fast Object Recognition Method Using Intersection of Projection Error Regions},
journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {19},
number = {5},
issn = {0162-8828},
year = {1997},
pages = {499-506},
doi = {http://doi.ieeecomputersociety.org/10.1109/34.589210},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - JOUR
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
TI - PERFORM: A Fast Object Recognition Method Using Intersection of Projection Error Regions
IS - 5
SN - 0162-8828
SP499
EP506
EPD - 499-506
A1 - Bharath R. Modayur,
A1 - Linda G. Shapiro,
PY - 1997
KW - Object recognition
KW - bounded error
KW - uncertainty regions
KW - parallel processing
KW - algorithm complexity.
VL - 19
JA - IEEE Transactions on Pattern Analysis and Machine Intelligence
ER -
 

Abstract—This paper describes a new formulation of the problem of object recognition under a bounded-error noise model and an object recognition methodology called PERFORM that finds matches by establishing correspondences between model and image features using this formulation. PERFORM evaluates correspondences by intersecting error regions in the image space. The algorithm is analyzed with respect to theoretical complexity as well as actual running times. When a single solution to the matching problem is sought, the time complexity of the sequential matching algorithm for 2D-2D matching using point features is of the order O(I3N2), where N is the number of model features and I is the number of image features. When line features are used, the sequential complexity is of the order O(I2N2). When a single solution is sought, PERFORM runs faster than the fastest known algorithm [8] to solve the bounded-error matching problem. The PERFORM method, which was developed with parallelizability as an important requirement, is shown to be easily realizable on both SIMD and MIMD architectures. The parallel versions of PERFORM are scalable, achieving linear speedups on both the MasPar and the KSR machines. When implemented in parallel, PERFORM does not require a large number of processors or memory, needs minimal to no inter-processor communication, requires no load balancing, and can produce all or just one solution to the matching problem. The communication-efficient version of PERFORM described in this paper has minimal memory requirements, since it only needs to store the model and image features and computes everything else on the fly.

[1] N. Ayache and O. D. Faugeras, "HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 1, pp. 44-54, 1986.
[2] H. S. Baird, Model-Based Image Matching Using Location.Cambridge, Mass.: MIT Press, 1985.
[3] D.H. Ballard, "Generalizing the Hough Transform to Detect Arbitrary Shapes," Pattern Recognition, vol. 13, no. 2, pp. 111-122, 1981.
[4] J. Ben-Arie, "The Probabilistic Peaking Effect of Viewed Angles and Distances With Application to 3D Object Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 8, pp. 760-774, August 1990.
[5] R.C. Bolles and R.A. Cain, "Recognizing and Locating Partially Visible Objects: The Local-Feature Focus Method," Int'l J. Robotics Res., vol. 1, no. 3, pp. 57-82, 1982.
[6] R.C. Bolles and P. Horaud, "3dpo: A Three-Dimensional Part Orientation System," Int'l J. Robotics Res., vol. 5, no. 3, pp. 3-26, 1986.
[7] T.M. Breuel, "Fast Recognition Using Adaptive Subdivisions of Transformation Space," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 445-451, June 1992.
[8] T.M. Breuel, Geometric Aspects of Visual Object Recognition, PhD thesis, Massachusetts Institute of Tech nology, 1992.
[9] O. Camps, L.G. Shapiro, and R.M. Haralick, "Premio: An Overview," IEEE Workshop on Directions in Automated CAD Based Vision, pp. 11-21, 1991.
[10] T.A. Cass, "Robust Parallel Computation of 2D Model-Based Recognition," Proc. Image Understanding Workshop,Boston, Mass., 1988. San Mateo, Calif.: Morgan and Kaufman, 1988.
[11] M.S. Costa, R.M. Haralick, and L.G. Shapiro, "Optimal Affine-Invariant Point Matching," Proc. 10th ICPR, vol. 1, pp. 233-236, 1990.
[12] M. Fischler and R. Bolles, "Random Sample Consensus: A Paradigm for Model Fitting With Applications to Image Analysis and Cartography," Comm. ACM, vol. 24, no. 6, pp. 381-395, 1981.
[13] W.E.L. Grimson, D.P. Huttenlocher, and D.W. Jacobs, "A Study of Affine Matching With Bounded Sensor Error," Lecture Notes in Computer Science, G. Sandini, ed., vol. 588, pp. 291-306, 1992.
[14] W.E.L. Grimson and T. Lozano-Perez, "Localizing Overlapping Parts by Searching the Interpretation Tree," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 4, pp. 469-482, 1987.
[15] D.P. Huttenlocher and S. Ullman, "Recognizing Solid Objects by Alignment With an Image," Int'l J. Computer Vision, vol. 5, no. 2, pp. 195-212, 1990.
[16] D.G. Lowe, "Three-Dimensional Object Recognition From Single Two-Dimensional Images," Artificial Intell., vol. 31, pp. 355-395, 1987.
[17] B. Modayur, "Fast Parallel Object Recognition With Adaptive Feature Extraction," Internal Report ISL-01-04-1994, Dept. of Electrical Engineering, FT-10, Univ. Washington, Apr. 1994.
[18] B. Modayur, "Selectivity Analysis of a Correspondence-Based Recognition Method," Internal Report ISL-01-08-1994, Dept. of Electrical Eng., FT-10, Univ. of Washington, Apr. 1994.
[19] B. Modayur and L.G. Shapiro, "Fast Parallel Object Recognition," Proc. Int'l Conf. Pattern Recognition, vol. D, pp. 284-289,Jerusalem, Israel, 1994.
[20] B.R. Modayur, Efficient Parallel Object Recognition, PhD thesis, Univ. of Washington, 1995.
[21] B.R. Modayur and L.G. Shapiro, "Parallel Algorithm for Object Recognition and Its Implementation on a Mimd Machine," CAMP '95 Computer Architectures for Machine Perception, pp. 313-322.Como, Italy, 1995.
[22] B.R. Modayur and L.G. Shapiro, "3D Matching Using Statistically Significant Groupings," Proc. ICPR96, vol. 1, pp. 238-242, 1996.
[23] C.F. Olson, "Fast Alignment Using Probabilistic Indexing," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 387-392, 1993.
[24] C.F. Olson, "Time and Space Efficient Pose Clustering," Proc. CVPR94, 1994, pp. 251-258.
[25] D. Thompson and J. Mundy, "Three-Dimensional Model Matching From an Unconstrained Viewpoint," Proc. IEEE Int'l Conf. Robotics and Automations, pp. 208-220, 1987.

Index Terms:
Object recognition, bounded error, uncertainty regions, parallel processing, algorithm complexity.
Citation:
Bharath R. Modayur, Linda G. Shapiro, "PERFORM: A Fast Object Recognition Method Using Intersection of Projection Error Regions," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 5, pp. 499-506, May 1997, doi:10.1109/34.589210
Usage of this product signifies your acceptance of the Terms of Use.