Abstract
Recently the idea of designing a computer system which automatically connects a number of independent vision modules together to solve a given computer vision problem has attracted significant interest. However the main assumption of this endeavour, namely that the modules used as the building blocks of the vision system are essentially fixed, is questionable in the light of previous experience. Therefore it is important to be able to modify even the detailed operation of the basic modules used, something which is not practical using conventional techniques.
This paper constructs a general method by which the computer code of a vision module can be altered automatically to make it mimic a desired behaviour. The system which does this, termed L, modifies a basic module template using interaction with an Oracle as a guide. The Oracle is an entity which, when given an input value, produces the corresponding output of the function which is to be mimicked. The system developed is based upon a new model of computation which endows it with the important properties that extracting the template (i.e. structure) of any module's computer code, as well as determining the best questions to pose to the Oracle are both performed automatically. Thus the L described has significant advantages over many other models which might be used (e.g. Neural Networks).
Dealing directly with this new model is not always convenient. Therefore a new computer language Madura is defined which provides a high-level interface to it. As Madura is syntactically similar to JAVA, it is simple to express the code of many basic vision modules in its terms and the results of L (the Madura code of a module which mimics the Oracle) are similarly simple to understand and use.
This paper shows a number of results which demonstrate how the L developed can learn many state-of-the-art initial vision algorithms in a matter of minutes. The current and future impact of this work is also examined.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
A.K. Bhattacharjya and B. Roysam, “Joint solution of low, intermediate, and high-level vision tasks by evolutionary optimisation: Application to computer vision at low SNR,” Neural Networks, Vol. 5, No. 1, pp. 83–95, 1994.
M. Brady, “Forms of knowledge in some machine vision systems,” Philosophical Transactions of the Royal Society: London Series B, Vol. 352, No. 1358, pp. 1241–1248, 1997.
D.S. Bridges, Computability: A Mathematical Sketchbook, Springer-Verlag, 1994.
K. Cho and P. Meer, “Image segmentation from consensus information,” CVGIP: Image Understanding, Vol. 68, No. 1, pp. 72–89, 1997.
R.I.D. Cowie, “Understanding shape: Perspectives from natural and machine vision,” Image and Vision Computing, Vol. 11, No. 6, pp. 307–308, 1993.
D. Crevier and R. Lepage, “Knowledge-based image understanding systems,” CVGIP: Image Understanding, Vol. 67, No. 2, pp. 161–185, 1997.
N.J. Cutland, Computability, Cambridge University Press, 1989.
E.R. Davies, Machine Vision, Academic Press, 1997.
B. Draper, A. Hanson, and E. Riseman, “Knowledge-directed vision: Control learning and integration,” Proceedings of the IEEE, Vol. 84, No. 11, pp. 1625–1637, 1996.
W.E.L. Grimson, Object Recognition by Computer, MIT Press, 1990.
W.E.L. Grimson, “The intelligent camera-Images of computer vision,” Proceedings of the National Academy of Sciences of the USA, Vol. 90, No. 21, pp. 9791–9794, 1993.
W.E.L. Grimson and J.L. Mundy, “Computer vision applications,” Communications of the ACM, Vol. 37, No. 3, pp. 45–51, 1994.
C. Harris and M. Stephens, “A combined corner and edge detector,” in AVC4, 1988, pp. 147–151.
P. Heller, S. Roberts, P. Seymour, and T. McGin, Java 1.1 Devlopers Handbook, SYBEX, 1997.
B.K.P. Horn, Robot Vision, MIT Press, 1986.
J. Bishop, Java Gently, Addison Wesley, 1997.
A. Jain and C. Dorai, “Practising vision: Integration, evaluation and applications,” Pattern Recognition, Vol. 30, No. 2, pp. 183–196, 1997.
R.C. Jain and T.O. Binford, “Ignorance, myopia, and naiveté in computer vision systems,” CVGIP-Image Understanding, Vol. 53, No. 1, pp. 112–117, 1991.
A. Kak, “Editorial,” CVGIP: Image Understanding, Vol. 61, No. 2, p. 153, 1995.
P. Maragos, “Tutorial on advances in morphological image processing and analysis,” Optical Engineering, Vol. 26, No. 7, pp. 623–632, 1987.
J.D. McCafferty, Human and Machine Vision, Chichester, West Sussex, England: Ellis Horwood, 1990.
M. Mirmehdi, P. Palmer, and J. Kittler, “Genetic optimisation of the image feature extraction process,” Pattern Recognition Letters, Vol. 18, No. 4, pp. 355–365, 1997.
R.A. Newman, “Automatic Learning in Computer Vision,” Ph.D. thesis, Oxford University, 1998. Available online at: ftp://ftp.robots.ox.ac.uk/pub/outgoing/newman/thesis.ps.gz.
R.A. Newman, “Automatic learning in computer vision,” 1998, in progress.
R.A. Newman, “A new model of computation for learning from examples,” Journal of Mathematical Imaging and Vision, Vol. 11, No. 1, pp. 45–63, 1999.
T. Pavlidis, “Why progress in computer vision is so slow,” Pattern Recognition Letters, Vol. 13, pp. 221–225, 1992.
P. Robertson and M. Brady, “Adaptive image analysis for aerial surveillance,” IEEE Intelligent Systems, Vol. 14, No. 3, May/June 1999.
S. Smith and M. Brady, “SUSAN-A new approach to low level image processing,” International Journal of Computer Vision, Vol. 23, No. 1, pp. 45–78, 1987.
Ø. Trier and A. Jain, “Goal-directed evaluation of binarisation methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 12, pp. 1191–1201, 1995.
Y. Venkatesh, “Some aspects of information processing in biological vision,” Current Science, Vol. 68, No. 2, pp. 168–184, 1995.
R. Vogt, Automatic Generation of Morphological Set Recognition Algorithms, Springer-Verlag, 1989.
H. Wechsler, Computational Vision, Academic Press, 1990.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Newman, R.A. Madura: A Language for Learning Vision Programs from Examples. Journal of Mathematical Imaging and Vision 11, 65–90 (1999). https://doi.org/10.1023/A:1008373328323
Issue Date:
DOI: https://doi.org/10.1023/A:1008373328323