This Article 
 Bibliographic References 
 Add to: 
The Multiple Window Parameter Transform
December 1992 (vol. 14 no. 12)
pp. 1157-1170

The multiwindow transform, an extension of parameter transform techniques that increase performance and scope by exploiting the long-range correlated information contained in multiple portions of an image, is presented. Multiple-window transforms allow the extraction of high-dimensional features with improvement in accuracy over conventional techniques while keeping linear to low-order-polynomial computational and space requirements with respect to image size and dimensionality of the features. Using correlated information provides a direct link between extracted features and supporting regions in the image. This, coupled with evidence integration techniques, is used to suppress noisy or nonexistent feature hypotheses. Parameter spaces are implemented as constraint satisfaction networks, where feature hypotheses with overlapping support in the image compete. After an iterative relaxation phase, surviving hypotheses have disjoint support, forming a segmentation of the image. Examples show the performance and provide insight about the behavior.

[1] D. H. Ballard, "Parameter nets: A theory of low level vision," inProc. 7th Int. Joint Conf. Artificial Intell., Aug. 1981, pp. 1068-1078.
[2] D. H. Ballard, Generalizing the Hough transform to detect arbitrary shapes,Patt. Recogn., vol. 13, no. 2, pp. 111-122, 1981.
[3] J. R. Bergen and Y. Shvayster, "Probabilistic algorithms for computing Hough transform," Sarnoff Lab Report.
[4] R. M. Bolle and S. S. Murty, "Curvature extraction from approximations to images or range data," IBM Tech. Rep., RC 12002, June 1986.
[5] R. M. Bolle and D. Sabbah, "Depth map processing for recognizing objects modeled by planes and quadrics of revolution," inProc. Intell. Auton. Syst., Dec. 1986, pp. 142-150.
[6] R. M. Bolle and D. Sabbah, "Differential geometry applied to least-square error surface approximations," inSPIE Conf. Opt. Digital Patt. Recogn., Jan. 1987, pp. 117-127.
[7] R. M. Bolle, R. Kjeldsen, and D. Sabbah, "Primitive shape extraction from range data," inProc. IEEE Workshop Comp. Vision, Nov./Dec. 1987, pp. 324-326.
[8] R. M. Bolle, A. Califano, R. Kjeldsen, and R. W. Taylor, "Visual recognition using concurrent and layered parameter networks," IBM Tech. Rep., Nov. 1988; IEEE Conf. Computer Vision and Pattern Recognition, 1989.
[9] R. M. Bolle, A. Califano, and R. Kjeldsen, "A complete and extendible approach to visual recognition,"IEEE Trans. Patt. Anal. Machine Intell., vol. 14, no. 5, pp. 534-548, May 1992.
[10] R. C. Bolles and P. Horaud, "3DPO: A three dimensional part orientation svstem,"Int. J. Robotics Res., vol. 5, no. 3, Fall 1986, pp. 3-26.
[11] F. L. Bookstein, "Fitting conic sections to scattered data,"Comp. Graphics Image Processing, vol. 9, no. 1, pp. 56-71, Jan. 1979.
[12] C. M. Bown, "Inherent bias and noise in the Hough transform,"IEEE Trans. Patt. Anal. Machine Intell., vol. 5, no. 5, pp. 493-505, Sept. 1983.
[13] A. Califano, "Feature recognition using correlated information contained in multiple neighborhoods," inProc 7th AAAI Nat. Conf. Artificial Intell., Aug. 1988, pp. 831-836.
[14] A. Califano, R. M. Bolle, and R. W. Taylor, "Generalized neighborhoods: A new approach to complex feature extraction," inProc. IEEE Conf. Comp. Vision Patt. Recogn., June 1989, pp. 192-199.
[15] A. Califano and R. Mohan, "Shape acquisition and recognition using spatial autocorrelation," IBM Tech. Rep., May 1990.
[16] A. Califano, R. Kjeldsen, and R. M. Bolle, "Data and model driven foveation," inProc. 10th Int. Conf. Patt. Recogn., June 1990, pp. 1-7.
[17] C. Dane and R. Bajcsy, "Three-dimensional segmentation using the Gaussian image and spatial information," inProc. IEEE Conf. Patt. Recogn. Image Processing, Aug. 1981, pp. 54-56.
[18] R.O. Duda and P.E. Hart, "Use of the Hough transformation to detect lines and curves in pictures,"Commun. Ass. Comput. Mach., vol. 15, no. 1, pp. 11-15, Jan. 1972.
[19] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[20] J. A. Feldman and D. H. Ballard, "Connectionist models and their properties,"Cognitive Sci., vol. 6, pp. 205-254, 1981.
[21] W. E. L. Grimson and D. P. Huttenlocher, "On the sensitivity of the Hough transform for object recognition,"IEEE Trans. Patt. Anal. Machine Intell., vol. 12, no. 3, pp. 255-274, Mar. 1990.
[22] K. Hanahara, T. Maruyama, and T. Uchiyama, "A real-time processor for the Hough transform,"IEEE Trans. Patt. Anal. Machine Intell., vol. 10, no. 1, pp. 121-125, Jan. 1988.
[23] P. V. C. Hough, "Methods and means for recognizing complex patterns," U. S. Patent 3 069 654, 1962.
[24] J. Illingworth and J. Kittler, "A survey of the Hough transform,"Comput. Vision Graphics Image Processing, vol. 44, pp. 87-116, 1988.
[25] D. J. Ittner and A. K. Jain, "3-D surface discrimination from local curvature measures," inProc. IEEE Conf. Comp. Vision Patt. Recogn., June 1985, pp. 119-123.
[26] A. K. Jain and R. C. Dubes,Algorithms for Clustering Data. Englewood Cliffs, NJ: Prentice-Hall, 1988.
[27] M. Kushnir, K. Abe, and K. Matsumoto, "Recognition of handprinted Hebrew characters using features selected in the Hough transform space,"Patt. Recogn., vol. 18, no. 2, pp. 103-113, 1985.
[28] J. R. Kender and R. Kjeldsen, "On seeing spaghetti: A radius-finding transform for flexible extruded objects under range data," IBM Tech. Rep., RC 16576, 1990.
[29] J. R. Kender and R. Kjeldsen, "On seeing spaghetti: A novel self-adjusting seven parameter Hough space for analyzing flexible extruded objects," IBM Tech. Rep., RC 16577, 1990.
[30] C. Kimme, D. Ballard, and J. Sklansky, "Finding circles by an array of accumulators,"Commun. ACM, vol. 18, pp. 120-122, Feb. 1975.
[31] P. Kultanen, L. Xu, and E. Oja, "Randomized Hough transform (RHT)," inProc. 10th Int. Conf. Patt. Recogn., June 1990, pp. 631-635.
[32] J. Lamperti,Stochastic Processes. New York: Springer-Verlag, 1977.
[33] A M. Liapounov, "Probleme generale de la stabilite du mouvement," inAnnals Math. Studies. Princeton, NJ: Princeton Univ. Press, 1947, no. 17.
[34] R. Mohan, "Constraints satisfaction networks for computer vision," inProgress in Neural Networks(O. Omidvar, Ed.). New York: Ablex, 1990.
[35] J. Neter and W. Wasserman,Applied Linear Statistical Models. Homewood, IL: Irwing, 1974.
[36] D. Pao, H. F. Li, and R. Jayakumar, "Detecting parametric curves using the straight line Hough transform," inProc. Int. Conf. Patt. Recogn., June 1990, pp. 620-625.
[37] A. Rosenfeld,Picture Processing by Computer. New York: Academic, 1969.
[38] D. Sabbah, "Computing with connections in visual recognition of origami objects,"Cognitive Sci., vol. 9, no. 1, pp. 25-50, Jan-Mar. 1985.
[39] S. D. Shapiro, "Properties of the transform for the detection of curves in noisy pictures,"Comput. Graphics Image Processing, vol. 8, pp. 219-236, 1978.
[40] S. D. Shapiro, "Feature space transforms for curve detection,"Patt. Recogn., vol. 10, pp. 129-143, 1978.
[41] J. Slansky, "On the Hough transform for curve detection,"IEEE Trans. Comput., vol. C-27, no. 10, pp. 923-926, Oct. 1978.
[42] G. Taubin, "Algebraic nonplanar curve and surface estimation in 3- space with applications to position estimation,"IEEE Trans. Patt. Anal. Machine Intell., vol. 13, no. 11, pp. 1115-1138, Nov. 1991.
[43] R. W. Taylor, "An efficient implementation of decomposable parameter spaces," inProc. 10th Int. Conf. Patt. Recogn., June 1990, pp. 613-619.

Index Terms:
computational requirements; feature dimensionality; feature extraction; parameter spaces; noisy feature hypothesis suppression; image segmentation; multiple window parameter transform; high-dimensional features; space requirements; image size; correlated information; evidence integration techniques; nonexistent feature hypotheses; constraint satisfaction networks; iterative relaxation phase; disjoint support; computational complexity; feature extraction; image processing; image segmentation; transforms
A. Califano, R.M. Bolle, "The Multiple Window Parameter Transform," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 12, pp. 1157-1170, Dec. 1992, doi:10.1109/34.177381
Usage of this product signifies your acceptance of the Terms of Use.