Abstract
We discuss design of vision modules, and discern three conceptual levels of design: the method (as the rationale behind the module as is usually reported in literature), the algorithm (the decomposition in computational steps) and the software code. We argue that at all stages, design goes hand in hand with performance in terms of aptness, correctness and figures of merit. We discuss the need, use and limitations of performance analysis. Also, we opt for a dual system design to include performance analysis in system architecture.
Preview
Unable to display preview. Download preview PDF.
References
H. S. Baird. Document image defect models and their uses. In K.Yamamoto, editor, Proc. ICDAR-93, pages 62–67. IEEE-Press, Los Alamitos, 1993.
R. Van Balen, T.ten Kate, D.Koelma, B.Mosterd, and AW.M.Smeulders. Scilimage: A multi-layered environment for use and development of image processing software. In Christensen and JL Crowley, editors, Experimental Environments for Computer Vision and Image Processing, pages 107–126. World Scient Press, 1993.
J. A. Bergstra, J. Heering, and P. Klint. Algebraic specification. Addison-Wesley, 1989.
T.H. Cormen, C. E. Leiserson, and R.L. Rivest. Introduction to algorithms. MIT press, 1992.
C. de Boer and A.W.M. Smeulders. A novel approach towards simulating graphics for performance analysis purposes. In Proc. Workshop GREC 1997, 1997.
J.G. den Hartog. A framework for knowledge-based map interpretation. PhD thesis, Technische Universiteit Delft, Delft, 1995.
R. Kasturi et al. A system for recognition and description of graphics. In Proc. 9th IAPR, Rome, pages 255–259, 1988.
W. Förstner. 10 pro's and con's against performance characterization of vision algorithms. In Proc., Workshop on Performance Characteristics of Vision Algorithms, Cambridge, 1996.
R.M. Haralick. Comments on performance characterization replies. Computer Vision and Image Understanding, 60:264–265, 1994.
R.M. Haralick. Performance characterization in computer vision. Computer Vision and Image Understanding, 60:245–249, 1994.
R.M. Haralick. Performance characterization protocol in computer vision. In Morgan Kaufmann, editor, Proc., ARPA Image Understanding Workshop (Monterey, CA, November 13–16, 1994), pages 667–673, San Francisco, CA, 1994.
A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher. An experimental comparison of range image segmentation algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(7):673–689, July 1996.
S.H. Joseph and T.P. Prodmore. Knowledge directed interpretation of mechanical engineering drawings. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 928–940, 1992.
T. Kanungo, M.Y. Jaisimha, J. Palmer, and R. M. Haralick. A methodology for quantitative performance evaluation of detection algorithms. IEEE Transactions on Image Processing, 4(12):1667–1674, 1995.
M.L. Kersten and F. Kwakkel. Design and implementation of a dbms performance assessment tool. In Proc. of the 4th intern. DEXA conference, pages 265–276, Prague, Czech Republic, 1993.
Kohl and Mundy. The development of the image understanding environment. In Proc. of the Conference on Computer Vision and Pattern Recognition, 1994.
B. Kong, I. T. Philips, R. M. Haralick, A. Prasad, and R. Kasturi. A benchmark: Performance evaluation of dashed-line detection algorithms. In R. Kasturi and K. Tombre, editors, Graphics Recognition — Methods and Applications, volume 1072 of Lecture Notes in Computer Science, pages 270–285. Springer-Verlag, May 1996.
M. Petrou M. Marik, J. Kittler. Error sensitivity assessment of vision algorithms based on direct error propagation. In Proc., Workshop on Performance Characteristics of Vision Algorithms, Cambridge, 1996.
T.Yamada S. Suzuki. Maris: map recognition input system. Pattern Recognition Letters, pages 919–933, 1990.
A. W. M. Smeulders and T. ten Kate. Software system design for paper map conversion. In R. Kasturi and K. Tombre, editors, Graphics Recognition — Methods and Applications, volume 1072 of Lecture Notes in Computer Science, pages 204–111. Springer-Verlag, May 1996.
R. v.d. Boomgaard. Mathematical Morphology: Extensions towards Computer Vision. PhD thesis, University of Amsterdam, 1992.
R. v.d. Boomgaard, L. Dorst, J. Schavemaker, and A.W.M. Smeulders. Quadratic structuring functions in mathematical morphology. In Mathematical Morphology and its applications to signal processing 3, 1996.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Smeulders, A.W.M., de Boer, C. (1998). Design and performance in object recognition. In: Tombre, K., Chhabra, A.K. (eds) Graphics Recognition Algorithms and Systems. GREC 1997. Lecture Notes in Computer Science, vol 1389. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64381-8_61
Download citation
DOI: https://doi.org/10.1007/3-540-64381-8_61
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64381-4
Online ISBN: 978-3-540-69766-4
eBook Packages: Springer Book Archive