Abstract
In this paper we propose recognizing logo images by using an adaptive model referred to as recursive artificial neural network. At first, logo images are converted into a structured representation based on contour trees. Recursive neural networks are then learnt using the contourtrees as inputs to the neural nets. On the other hand, the contour-tree is constructed by associating a node with each exterior or interior contour extracted from the logo instance. Nodes in the tree are labeled by a feature vector, which describes the contour by means of its perimeter, surrounded area, and a synthetic representation of its curvature plot. The contour-tree representation contains the topological structured information of logo and continuous values pertaining to each contour node. Hence symbolic and sub-symbolic information coexist in the contour-tree representation of logo image. Experimental results are reported on 40 real logos distorted with artificial noise and performance of recursive neural network is compared with another two types of neural approaches.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
F. Cesarini, E. Francesconi, M. Gori, S. Marinai, J. Q. Sheng, and G. Soda, “Rectangle labelling for an invoice understanding system,” in Proceedings of the International Conference on Document Analysis and Recognition, pp. 324–330, Ulm, Germany, August 18–20 1997.
D. Doermann, E. Rivlin, and I. Weiss, “Applying algebraic and differential invariants for logo recognition,” Machine Vision and Applications, vol. 9, no. 2, pp. 73–86, 1996.
G. Cortelazzo G. A. Mian, G. Vezzi, and P. Zamperoni, “Trademark shapes description by string-matching techniques,” Pattern Recognition, vol. 27, no. 8, pp. 1005–1018, 1994.
K. Hachimura, “Decomposition of hand-printed patterns,” Proceedings of the International Conference on Pattern Recognition, pp. 417–420, 1992.
F. Cesarini, M. Gori, S. Marinai, and G. Soda, “A hybrid system for locating and recognizing low level graphic items,” in Graphics Recognition (R. Kasturi and K. Tombre, eds.), pp. 135–147, LNCS, Vol. 1072, Springer Verlag, March 1996.
F. Cesarini, E. Francesconi, M. Gori, S. Marinai, J. Sheng, and G. Soda, “A neural based architecture for spot-noisy logo recognition,” in Proceedings of the International Conference on Document Analysis and Recognition, pp. 175–179, Ulm, Germany, August 18–20 1997.
A. Spercluti and A. Starita, “Supervised neural networks for the classification of structures,” IEEE Transaction on Neural Networks, vol. 8, no. 3, pp. 714–735, 1997.
J. Thacher, “Tree automata: An informal survey,” in Currents in the Theory of Computing (A. Aho, ed.), pp. 143–173, Englewood Cliffs: Prentice-Hall Inc., 1973.
R. C. Gonzalez and M. G. Thomason, Syntactic Pattern Recognition, An Introduction. Reading, Massachusettes: Addison Wesley, 1978.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning internal representation by error propagation,” in Parallel Distributed Processing, vol. 1, ch. 8, pp. 318–363, Cambridge: MIT Press, 1986.
R. Williams and D. Zipser, “Gradient-based learning algorithms for recurrent networks and their computational complexity,” Backpropagation. Theory, Architectures, and Applications, In Y. Chauvin and D.E. Rumelhart (Eds.), Lawrence Erlbaum Associates, 1995.
T. Pavlidis, Algorithms for Graphics and Image Processing. Computer Science Press, 1982.
W. McKee and J. Aggarwal, “Computer recognition of partial views of curved objects,” IEEE Trans. Computers, vol. 26, no. 8, pp. 790–800, 1977.
H. S. Baird, “Document image defect models,” in Structured Document Image Analysis (H.S. Baird, H. Bunke and K. Yamamoto eds.) pp. 546–556, Springer Verlag, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Francesconi, E. et al. (1998). Logo recognition by recursive neural networks. 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_43
Download citation
DOI: https://doi.org/10.1007/3-540-64381-8_43
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