Deformable Template Matching within a Bayesian Framework for Hand-Written Graphic Symbol Recognition
- 366 Downloads
We describe a method for hand-drawn symbol recognition based on deformable template matching able to handle uncertainty and imprecision inherent to hand-drawing. Symbols are represented as a set of straight lines and their deformations as geometric transformations of these lines. Matching, however, is done over the original binary image to avoid loss of information during line detection. It is defined as an energy minimization problem, using a Bayesian framework which allows to combine fidelity to ideal shape of the symbol and flexibility to modify the symbol in order to get the best fit to the binary input image. Prior to matching, we find the best global transformation of the symbol to start the recognition process, based on the distance between symbol lines and image lines. We have applied this method to the recognition of dimensions and symbols in architectural floor plans and we show its flexibility to recognize distorted symbols.
KeywordsInput Image Prior Probability Bayesian Inference Bayesian Framework Ideal Shape
Unable to display preview. Download preview PDF.
- 2.A. K. Chhabra. Graphic symbol recognition: An overview. In K. Tombre and A. K. Chhabra, editors, Graphics Recognition: Algorithms and Systems, pages 68–79. Springer Verlag, Berlin, 1998. 193Google Scholar
- 3.A. H. Habacha. Structural recognition of disturbed symbols using discrete relaxation. In Proceedings of 1st. International Conference on Document Analysis and Recognition, pages 170–178, Sep-Oct 1991. Saint Malo, France. 193Google Scholar
- 6.P. Kuner and B. Ueberreiter. Knowledge-based pattern recognition in disturbed line images using graph theory, optimization and predicate calculus. In Proceedings of 8th. International Conference on Pattern Recognition, pages 240–243, October 1986. Paris, France. 193Google Scholar
- 7.P. J. M. Van Laarhoven and E. H. Aarts. Simulated Annealing: Theory and Applications. Kluwer Academic Publishers, 1989. 198Google Scholar
- 8.S. Lee. Recognizing hand-written electrical circuit symbols with attributed graph matching. In H. S. Baird, H. Bunke, and K. Yamamoto, editors, Structured Document Analysis, pages 340–358. Springer Verlag, Berlin, 1992. 193Google Scholar
- 10.G. J. MacLachlan and T. Krishnan. The EM algorithm and extensions. John Wiley and Sons, Inc., 1997. 201Google Scholar
- 11.B. T. Messmer and H. Bunke. Automatic learning and recognition of graphical symbols in engineering drawings. In R. Kasturi and K. Tombre, editors, Graphics Recognition: Methods and Applications, Selected Papers from First International Workshop on Graphics Recognition, 1995, pages 123–134. Springer, Berlin, 1996. Volume 1072 of Lecture Notes in Computer Science. 193Google Scholar
- 14.E. Valveny and E. Martí. Application of deformable template matching to symbol recognition in hand-written architectural drawings. In Fifth IAPR International Conference on Document Analysis and Recognition ICDAR’99, pages 483–486, Bangalore, India, September 1999. 194Google Scholar