Integrating Low and High Level Object Recognition Steps by Probabilistic Networks

In pattern recognition applications the low level segmentation and the high level object recognition are generally considered as two separate steps. The paper presents a method that bridges the gap between the low and the high level object recognition. It is based on a Bayesian network representation and network propagation algorithm. At the low level it uses hierarchical structure of quadratic spline wavelet image bases. The method is demonstrated for a simple circuit diagram component identification problem.

• András Barta
• István Vajk

• Object recognition
• Bayesian network
• Wavelets
• Document processing.

[1] Barta A, Vajk I., Document Image Analysis by Probabilistic Network
and Circuit Diagram Extraction, Informatica, An International Journal
of Computing and Informatics, 29, pp. 291-301, 2005
[2] Barta A., Vajk I, Processing Circuit Diagrams with Belief Network and
Intelligent Agents., Transactions on Information Science and
Applications, Issue 9, Vol. 2, September, pp. 1321-1329, 2005
[3] Draper B., Hanson H., Riseman E., Knowledge-Directed Vision:
Control, Learning and Integration,http://www.cs.colostate.edu/ ~draper/
publications/draper_ieee96.pdf Proceedings of the IEEE, 84(11), pp.
1625-1637, 1996
[4] Neopolitan R. E., Learning Bayesian networks, Pearson Prentice Hall,
2004
[5] Pearl, J., Probabilistic Reasoning in Intelligent Systems: Networks of
Plausible Interference, Morgan Kauffmann Publishers, 1988
[6] Okazaki A., Kondo T., Mori K., Tsunekawa S., Kawamoto E., An
Automatic Circuit Diagram Reader With Loop-Structure-Based Symbol
Recognition, IEEE Trans. Pattern Analysis and Machine Intelligence,
Vol. 10, No. 3, pp. 331-341, May 1988
[7] Takatsuka M., Caelli T. M., West G. A. W., Venkatesh S., An
application of ÔÇÿÔÇÿagent-oriented-- techniques to symbolic matching and
object recognition, Pattern Recognition Letters 23, pp. 419-429, 2002
[8] Siddiqi K., Subrahmonia J., Cooper D., Kimia B.B., Part-Based
Bayesian Recognition Using Implicit Polynomial Invariants,
Proceedings of the 1995 International Conference on Image Processing
(ICIP), pp. 360-363, 1995
[9] Storkey A.J., Williams C.K.I., Image Modeling with Position-Encoding
Dynamic Trees, IEEE Trans. Pattern Analysis and Machine Intelligence,
Vol. 25, No. 7, July pp. 859-871, 2003
[10] Zou Song-Chun, Statistical Modeling and Conceptualization of Visual
Patterns, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.
25, No. 6, June, pp 691-712, 2003
[11] Mallat S., A Wavelet Tour of Signal Processing, Academic Press, 1999
[12] Burrus C. S, Introduction to Wavelets and Wavelet Transforms, Prentice
Hall, 1998
[13] Freeman T.W., Adelson E.H., The Design and Use of Steerable Filters,
IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 13, No. 9,
September, pp 891-906, 1991
[14] Sung J., Bang S.J., Choi S., A Bayesian network classifier and
hierarchical Gabor features for Handwritten Numeral Recognition,
Pattern Recognition Letters, 27. pp 66-75, 2006
[15] Deng S., Lati S., Regentova E., Document segmentation using
polynomial spline wavelets, Pattern Recognition, 34. pp. 2533-2545,
2001
[16] Olshausen B.A, Anderson C.H., Van Essen D.C., A neurobiological
model of visual attention and invariant pattern recognition based
dynamic routing information, The Journal of Neuroscience, 13(11),
4700-4719, 1993