This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Robust and Efficient Detection of Salient Convex Groups
January 1996 (vol. 18 no. 1)
pp. 23-37
ASCII Text
x 
 
David W. Jacobs, "Robust and Efficient Detection of Salient Convex Groups," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 1, pp. 23-37, January, 1996.
 
 
BibTex
x
 
@article{ 10.1109/34.476008,
author = {David W. Jacobs},
title = {Robust and Efficient Detection of Salient Convex Groups},
journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {18},
number = {1},
issn = {0162-8828},
year = {1996},
pages = {23-37},
doi = {http://doi.ieeecomputersociety.org/10.1109/34.476008},
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 - Robust and Efficient Detection of Salient Convex Groups
IS - 1
SN - 0162-8828
SP23
EP37
EPD - 23-37
A1 - David W. Jacobs,
PY - 1996
KW - Grouping
KW - perceptual organization
KW - convexity
KW - proximity
KW - nonaccidental properties
KW - robust
KW - efficiency
KW - recognition.
VL - 18
JA - IEEE Transactions on Pattern Analysis and Machine Intelligence
ER -
 

Abstract—This paper describes an algorithm that robustly locates salient convex collections of line segments in an image. The algorithm is guaranteed to find all convex sets of line segments in which the length of the gaps between segments is smaller than some fixed proportion of the total length of the lines. This enables the algorithm to find convex groups whose contours are partially occluded or missing due to noise. We give an expected case analysis of the algorithm's performance. This demonstrates that salient convexity is unlikely to occur at random, and hence is a strong clue that grouped line segments reflect underlying structure in the scene. We also show that our algorithm's run time is O(n2 log(n) + nm), when we wish to find the m most salient groups in an image with n line segments. We support this analysis with experiments on real data, and demonstrate the grouping system as part of a complete recognition system.

[1] T.D. Alter, "The role of saliency and error propagation in visual object recognition," PhD thesis, MIT, 1995.
[2] R. Basri and D. Jacobs, "Recognition using region correspondences," Proc. IEEE Int'l Conf. on Computer Vision, pp. 8-15, 1995.
[3] I. Bergevin and M.D. Levine, "Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings," IEEE Trans. Pattern Recognition and Machine Intelligence, vol. 15, no. 1, pp. 19-36, Jan. 1993.
[4] I. Biederman, "Human image understanding: Recent research and a theory," Computer Graphics, Vision, and Image Processing, vol. 32, pp. 29-73, 1985.
[5] T. Binford, "Inferring surfaces from images," Artificial Intelligence, vol. 17, pp. 205-244, 1981.
[6] M. Boldt, R. Weiss, and E. Riseman, “Token-Based Extraction of Straight Lines,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 6, pp. 1581-1595, June 1989.
[7] J.B. Burns and E. Riseman, "Matching complex images to multiple 3D objects using view description networks," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 328-334, 1992.
[8] A. Califano and R. Mohan, "Multidimensional Indexing for Recognizing Visual Shapes," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 4, pp. 373-392, 1994.
[9] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, June 1986.
[10] D. Clemens, "Region-based feature interpretation for recognizing 3D models in 2D images," Technical Report AI TR-1307, MIT, 1991.
[11] D. Clemens and D. Jacobs, "Space and time bounds on model indexing," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 10, pp. 1,007-1,018, 1991.
[12] I.J. Cox, J.M. Rehg, and S. Hingorani, “A Bayesian Multi-Hypothesis Approach to Edge Grouping and Contour Segmentation,” Int'l J. Computer Vision, vol. 11, no. 1, pp. 5-24, 1993.
[13] S. Denasi, G. Quaglia, and D. Rinaudi, "The use of perceptual organization in the prediction of geometric structures," Pattern Recognition Letters, vol. 13, no. 7, pp. 529-539, 1991.
[14] J. Dolan and E. Riseman, “Computing Curvilinear Structure by Token-Based Grouping,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 264-270, 1992.
[15] J. Elder and S. Zucker, "A measure of closure," Vision Research, vol. 34, no. 24 pp. 3,361-3,370.
[16] L. Finkel and P. Sajda, "Object discrimination based on depth-from-occlusion," Neural Computation, vol. 4, no. 6, pp. 901-921, 1992.
[17] W.E.L. Grimson, Object Recognition by Computer. MIT Press, 1990.
[18] G. Guy and G. Medioni, "Inferring global perceptual contours from local features," DARPA Image Understanding Workshop, pp. 881-892, 1993.
[19] R. Heitger and R. Von der Heydt, "A computational model of neural contour processing, figure-ground segregation and illusory contours," Proc. IEEE Int'l Conf. Computer Vision, pp. 32-40, 1993.
[20] L. Herault and R. Horaud, “Figure Ground Discrimination: A Combinatorial Optimization Method,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 15, no. 9, pp. 899-914, Sept. 1993.
[21] D. Hoffman and W. Richards, "Parts of recognition," Visual Cognition, S. Pinker, ed. Cambridge, Mass.: MIT Press, 1984.
[22] J. Hu, B. Sakoda, and T. Pavlidis, "Interactive road finding for aerial images," Proc. IEEE Workshop Applications of Computer Vision, pp. 56-63, 1992.
[23] T. Huang, "Reply: Computer vision needs more experiments and applications," Computer Vision, Graphics, and Image Processing, vol. 53, no. 1, pp. 125-126, 1991.
[24] D. Huttenlocher and P. Wayner, “Finding Convex Edge Groupings in an Image,” Int'l J. Computer Vision, vol. 8, no. 1, pp. 7-27, 1992.
[25] D. Jacobs, "GROPER: A grouping based object recognition system for two-dimensional objects," Proc. IEEE Workshop Computer Vision, pp. 164-169, 1987.
[26] D.W. Jacobs, “Grouping for Recognition,” MIT AI Memo 1177, 1989.
[27] D. Jacobs, "Space efficient 3D model indexing," IEEE Conf. Computer Vision and Pattern Recognition, pp. 439-444, 1992.
[28] D. Jacobs, "Recognizing 3-D objects using 2-D images," MIT AI TR-1416, 1992.
[29] D.W. Jacobs, Robust and Efficient Detection of Convex Groups Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 770-771, 1993.
[30] D. Jacobs, "Finding salient convex groups," Proc. DIMACS Workshop Partitioning Data Sets: with Applications to Psychology, Vision, and Target Tracking, 1995.
[31] A. Kalvin, E. Schonberg, J.T. Schwartz, and M. Sharir, “Two-Dimensional, Model-Based, Boundary Matching Using Footprints,” Int'l J. Robotics Research, vol. 5, no. 4, pp. 38-55, 1986.
[32] T. Kanade, "Recovery of the three-dimensional shape of an object from a single view," Artificial Intelligence, vol. 17, pp. 409-460, 1981.
[33] G. Kanisza and W. Gerbino, "Convexity and symmetry in figure-ground organization," Vision and Artifact, M. Henle, ed. New York: Springer, 1976.
[34] P. Kellman and T. Shipley, "A theory of visual interpolation in object perception," Cognitive Psychology, vol. 23, pp. 141-221, 1991.
[35] W. Kohler, Gestalt Psychology.New York: Mentor Books, 1959.
[36] I. Kovacs and B. Julesz, "A closed curve is much more than an incomplete one: Effect of closure in figure-ground segmentation." Proc. Nat'l Academy of Science, USA, vol. 90, pp. 7,495-7,497, 1993.
[37] M. Kubovy and J. Pomerantz, Perceptual Organization.Hillsdale N.J.: Lawrence Erlbaum Associates, 1981.
[38] D.G. Lowe, Perceptual Organization and Visual Recognition. Boston: Kluwer Academic, 1985.
[39] D.G. Lowe, “Three-Dimensional Object Recognition from Single Two-Dimensional Images,” Artificial Intelligence, vol. 31, pp. 355-395, 1987.
[40] J. Mahoney, "Image chunking: Defining spatial building blocks for scene analysis," MIT AI TR-980, 1987.
[41] D. Marr, "Artificial intelligence—A personal view," Artificial Intelligence, vol. 9, pp. 37-48, 1977.
[42] R. Mohan and R. Nevatia, “Using Perceptual Organization to Extract 3-D Structures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 11, pp. 1,121-1,139, Nov. 1989.
[43] R. Mohan and R. Nevatia, "Perceptual Organization for Scene Segmentation and Description," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 6, pp. 616-635, June 1992.
[44] M. Nitzburg and D. Mumford, "The 2.1-D sketch," Proc. IEEE ICCV, pp. 138-144, 1990.
[45] P. Parent and S.W. Zucker, “Trace Inference, Curvature Consistency and Curve Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 8, pp. 823-839, 1989.
[46] T. Pavlidis and S. Horowitz, "Segmentation of plane curves," IEEE Trans. Computers, vol. 23, pp. 860-870, 1974.
[47] A. Pentland, "Recognition by parts." Proc. First Int'l Conf. Computer Vision, pp. 612-620, 1987.
[48] G. Reynolds and J.R. Beveridge, Proc. DARPA Image Understanding Workshop, pp. 257-271, 1987.
[49] W. Richards and A. Jepson, "What makes a good feature?" MIT AI Memo 1356, 1992.
[50] S. Sarkar and K.L. Boyer, "Integration, Inference, and Management of Spatial Information Using Bayesian Networks: Perceptual Organization," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 3, pp. 256-274, Mar. 1993. Special Section on Probabilistic Reasoning.
[51] E. Saund, “Identifying Salient Circular Arcs on Curves,” CVGIP: Image Understanding, vol. 58, no. 3, pp. 327-337, 1993.
[52] H. Sawhney, "Trackability as a cue for potential obstacleidentification and 3D description," Int'l J. Computer Vision, vol. 11, no. 3, pp. 237-266, 1993.
[53] A. Sha'ashua and S. Ullman, “Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network,” Proc. Int'l Conf. Computer Vision, pp. 321-327, 1988.
[54] T.F. Syeda-Mahmood, “Data and Model-Driven Selection Using Closely-Spaced Parallel-Line Groups,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 881-885, 1994.
[55] D. Trytten and M. Tuceryan, "Segmentation and grouping of object boundaries using energy minimization," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 730-731, 1991.
[56] P. Wayner, "Efficiently using invariant theory for model-based matching," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 473-478, 1991.
[57] L. Williams, "Perceptual organization of occluding contours," Proc. IEEE Int'l Conf. Computer Vision, pp. 133-137, 1990.
[58] A. Witkin and J. Tenenbaum, "On the role of structure in vision," Human and Machine Vision, Beck, Hope, and Rosenfeld, eds. New York: Academic Press, 1983.
[59] M. Zerroug and R. Nevatia, "Using invariance and quasi-invariance for the segmentation and recovery of curved objects," Applications of Invariance in Computer Vision, J. Mundy and A. Zisserman, eds. Berlin, Heidelberg: Springer-Verlag, 1994.
[60] S. Zucker, "Cooperative grouping and early orientation selection," Physical and Biological Processing of Images, Braddick and Sleigh, eds. Berlin: Springer-Verlag, 1983.

Index Terms:
Grouping, perceptual organization, convexity, proximity, nonaccidental properties, robust, efficiency, recognition.
Citation:
David W. Jacobs, "Robust and Efficient Detection of Salient Convex Groups," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 1, pp. 23-37, Jan. 1996, doi:10.1109/34.476008
Usage of this product signifies your acceptance of the Terms of Use.