
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
D. Keren, M. Werman, "Probabilistic Analysis of Regularization," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 982995, October, 1993.  
BibTex  x  
@article{ 10.1109/34.254057, author = {D. Keren and M. Werman}, title = {Probabilistic Analysis of Regularization}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {15}, number = {10}, issn = {01628828}, year = {1993}, pages = {982995}, doi = {http://doi.ieeecomputersociety.org/10.1109/34.254057}, 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  Probabilistic Analysis of Regularization IS  10 SN  01628828 SP982 EP995 EPD  982995 A1  D. Keren, A1  M. Werman, PY  1993 KW  probabilistic analysis; reliability measures; regularization; interpolated data; confidence measures; probability structure; variance; Boltzmann distribution; functional analysis; measure theory; depth images; image processing; probability; reliability VL  15 JA  IEEE Transactions on Pattern Analysis and Machine Intelligence ER   
In order to use interpolated data wisely, it is important to have reliability and confidence measures associated with it. A method for computing the reliability at each point of any linear functional of a surface reconstructed using regularization is presented. The proposed method is to define a probability structure on the class of possible objects and compute the variance of the corresponding random variable. This variance is a natural measure for uncertainty, and experiments have shown it to correlate well with reality. The probability distribution used is based on the Boltzmann distribution. The theoretical part of the work utilizes tools from classical analysis, functional analysis, and measure theory on function spaces. The theory was tested and applied to real depth images. It was also applied to formalize a paradigm of optimal sampling, which was successfully tested on real depth images.
[1] R. A. Adams,Sobolev Spaces. New York: Academic, 1975.
[2] H. Akima, "Bivariate interpolation and smooth surface fitting based on local procedures,"Comm. ACM, vol. 17, pp. 2631, 1974.
[3] N. Ayache and O. D. Faugeras, "Building, registrating and fusing noisy visual maps," inProc. Int. Conf. Comput. Vision(London), May 1987, pp. 7382.
[4] M. Bertero, T. A. Poggio, and V. Torre, "Illposed problems in early vision,"Proc. IEEE, vol. 76, pp. 869889, Aug. 1988.
[5] A. Blake and A. Zisserman,Visual Reconstruction. Cambridge, MA: MIT Press, 1987.
[6] R. J. Chorley,Spatial Analysis in Geomorphology. New York: Methuen, 1972.
[7] P. Craven and G. Whaba, "Optimal smoothing of noisy data with spline functions,"Numerische Mathematik, vol. 31, pp. 377403, 1979.
[8] S. Geman and D. Geman, "Stochastic relaxation, gibbs distribution, and the bayesian restorat ion of images,"IEEE Trans. on Patt. Anal. Machine Intell., vol. 6, pp. 721741, June 1984.
[9] L. Gross, "Integration and nonlinear transformations in hilbert space,"Trans. Amer. Math. Soc., vol. 94, pp. 404440, 1960.
[10] B. K. P. Horn,Robot Vision. Cambridge, MA: M.I.T. Press, 1986.
[11] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Artificial Intell., vol. 17, pp. 185203, 1981.
[12] D. Keren, "Probabilistic analyses of interpolation in computer vision," Ph.D. thesis, Hebrew Univ. of Jerusalem, 1990.
[13] J. Kuelbs, F. M. Larkin, and J. A. Williamson, "Weak probability distributions on reproducing kernel hilbert spaces,"Rocky Mountain J. Math., vol. 2, pp. 369378, 1972.
[14] H. H. Kuo,Gaussian Measures in Banach Spaces. New York: SpringerVerlag, 1975.
[15] F. M. Larkin, "Gaussian measure in hilbert space and applications in numerical analysis,"Rocky Mountain J. Math., vol. 2, pp. 379421, 1972.
[16] Y. G. Leclerc, "Image and boundary segmentation via minimallength encoding on the connection machine," inProc. Image Understanding Workshop, 1989, pp. 10561069.
[17] D. Lee, "Approximation of linear operators on a wiener space,"Rocky Mountain J. Math., vol. 16, pp. 641659, 1986.
[18] J. L. Marroquin, "Deterministic bayesian estimation of markovian random fields with applications to computational vision," inProc. Int. Conf. Comput. Vision(London), May 1987, pp. 597601.
[19] L. Matthies, T. Kanade, and R. Szeliski, "Kalman filterbased algorithms for estimating depth from image sequences,"Int. J. Comput. Vision, vol. 3, pp. 209236, 1989.
[20] L. Matthies, R. Szeliski, and T. Kanade, "Incremental estimation of dense depth maps from image sequences," inProc. IEEE Conf. Comput. Vision Patt. Recogn., (Ann Arbor), June 1988, pp. 366374.
[21] D. Mumford and J. Shah, "Boundary detection by minimizing functionals," inProc. IEEE Conf. Comput. Vision Patt. Recogn.(San Francisco), June 1985, pp. 2226.
[22] T. Poggio, D. Voorhies, and A. Yuille,MIT A.I. Memo 833, Mass Inst. Technol., May 1985.
[23] W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling,Numerical Recipes. Cambridge, UK: Cambridge Univ. Press, 1986.
[24] M. Rioux and L. Cournoyer, "The NRCC threedimensional image data files," Nat. Res. Council Canada, 1988.
[25] J. E. Robinson, H. A. K. Charlesworth, and M. J. Ellis, "Structural analysis using spatial filtering in interior plans of southcentral Alberta,"Amer. Assoc. Petrol. Geol. Bull., vol. 53, pp. 23412367, 1969.
[26] A. Shmuel and M. Werman, "Active vision: 3d from an image sequence," inProc. Int. Conf. Patt. Recogn., (Atlantic City), June 1990, pp. 4854.
[27] R. Szeliski, "Regularization uses fractal priors," inProc. Nat. Conf. Artificial Intell., 1987, pp. 749754.
[28] R. Szeliski,Bayesian Modeling of Uncertainty in LowLevel Vision, Boston: Kluwer, 1989.
[29] D. Terzopoulos, "Multilevel surface reconstruction,"Multiresolution Image Processing and Analysis. (A. Rosenfeld, Ed.). New York: SpringerVerlag, 1984.
[30] D. Terzopoulos, "Regularization of inverse visual problems involving discontinuities,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI8, no. 4, pp. 413424, July 1986.
[31] A. N. Tikhonov and V. Y. Arsenin,Solution of IllPosed Problems. New York: Winston, 1977.
[32] G. W. Wasilkowski, "Optimal algorithms for linear problems with gaussian measures,"Rocky Mountain J. Math., vol. 16, pp. 727749, 1986.
[33] J. Weng, T. S. Huang, and N. Ahuja, "Motion and structure from two perspective views: Algorithms, error analysis, and error estimation,"IEEE Trans. Patt. Anal. Machine Intell., vol. 11, pp. 451476, 1989.
[34] G. Whaba, "Bayesian confidence intervals for the cross validated smoothing spline," Techn. Rep. Dept. of Stat., Univ. of Wisconsin, 1981.
[35] N. Young,An Introduction to Hilbert Space.\quad Cambridge, MA:Cambridge Mathematical Textbooks, 1988.