This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Illumination Planning for Object Recognition Using Parametric Eigenspaces
December 1994 (vol. 16 no. 12)
pp. 1219-1227

Presents a novel approach to the problem of illumination planning for robust object recognition in structured environments. Given a set of objects, the goal is to determine the illumination for which the objects are most distinguishable in appearance from each other. Correlation is used as a measure of similarity between objects. For each object, a large number of images is automatically obtained by varying the pose and the illumination direction. Images of all objects together constitute the planning image set. The planning set is compressed using the Karhunen-Loeve transform to obtain a low-dimensional subspace, called the eigenspace. For each illumination direction, objects are represented as parametrized manifolds in the eigenspace. The minimum distance between the manifolds of two objects represents the similarity between the objects in the correlation sense. The optimal source direction is therefore the one that maximizes the shortest distance between the object manifolds. Several experiments have been conducted using real objects. The results produced by the illumination planner have been used to enhance the performance of an object recognition system.

[1] B. G. Batchelor, "A Prolog lighting advisor,"SPIE Proc. Intelligent Robots and Computer Vision VIII: Systems and Applications, B. G. Batchelor, Ed., vol. 1193, 1993.
[2] C. Cowan and A. Bergman, "Determining the camera and light source location for a visual task," inProc. IEEE Int. Conf. Robotics and Automation, pp. 509-514, 1989.
[3] C. Cowan, and D. Nitzan, "Automatic placement of vision sensors" inProc. 18th Annual NSF Conf. Design and Manufacturing Systems, Georgia Tech University, Atlanta, GA, Jan., 1992.
[4] H. Murase, F. Kimura, M. Yoshimura, and Y. Miyake, "An improvement of the auto-correlation matrix in pattern matching method and its application to handprinted 'HIRAGANA',"Trans. IECE, vol. J64-D, no. 3, 1981.
[5] H. Murase and M. Lindenbaum, "Spatial temporal adaptive method for partial eigenstructure decomposition of large images," NTT Tech. Rep. No. 6527, Mar. 1992. Also inIEEE Trans. Image Processing, in press.
[6] H. Murase and S. K. Nayar, "Visual learning and recognition of 3D objects from appearance,"Int. J. Comput. Vision, vol. 14, 1995.
[7] H. Murase and S. K. Nayar, "Illumination planning for object recognition in structured environments," inProc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 31-38, 1994.
[8] E. Oja,Subspace methods of Pattern Recognition. Hertfordshire: Research Studies, 1983.
[9] W. Press, B. Flannery, S. Teukolsky, and W. Vetterling,Numeric Recipes in C-The Art of Scientific Computing.Cambridge, UR: Cambridge University Press, 1988.
[10] S. Sakane, M. Sato, and M. Kakikura, "Automatic planning of light source placement for an active photometric stereo system," inProc. IEEE Int. Workshop on Intelligent Robots and Systems, pp. 559-566, 1990.
[11] M. A. Turk and A. P. Pentland, "Face recognition using eigenfaces," inProc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 586-591, June 1991.
[12] S. Yi, R. M. Haralick, and L. G. Shapiro, "Optimal sensor and light source positioning for machine vision," inProc. Int. Conf. Pattern Recognition, 1990.
[13] S. Yi, "Illumination control expert for machine vision: A goal driven approach," Ph.D. dissertation, Dept. of Computer Science and Engineering. Univ. of Washington, Seattle, Mar. 1990.

Index Terms:
object recognition; lighting; planning; brightness; correlation methods; correlation theory; data compression; image coding; eigenvalues and eigenfunctions; transforms; illumination planning; robust object recognition; parametric eigenspaces; structured environments; distinguishability; correlation; similarity measure; illumination direction; planning image set compression; Karhunen-Loeve transform; low-dimensional subspace; parametrized manifolds; minimum distance; optimal source direction; image compression; principal component analysis; appearance matching; parametric appearance representation; pose invariance
Citation:
H. Murase, S.K. Nayar, "Illumination Planning for Object Recognition Using Parametric Eigenspaces," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 12, pp. 1219-1227, Dec. 1994, doi:10.1109/34.387485
Usage of this product signifies your acceptance of the Terms of Use.