A progressive learning method for symbols recognition

ABSTRACT

This paper deals with a progressive learning method for symbols recognition which improves its own recognition rate when new symbols are recognized in graphics documents. We propose a discriminant analysis method which provides allocation rules from learning samples with known classes. However a discriminant analysis method is efficient only if learning samples and data are defined in the same conditions but it is rare in real life. In order to overcome this problem, a conditional vector is added to each observation to take into account the parasitic effects between the data and the learning samples. We propose also an adaptation to consider the user feedback.

REFERENCES

• 1: S. Adam, J. Ogier, C. Cariou, R. Mullot, J. Labiche, and J. Gardes. Symbol and character recognition: application to engineering drawings. International Journal on Document Analysis and Recognition, 3(2), 2001.
• 2: A. Baccini, H. Caussinus, and A. Ruiz-Gazen. Apprentissage progressif en analyse discriminante. Revue de Statistique Appliquée, 49, 2001.
• 3: Anil K. Jain , Robert P. W. Duin , Jianchang Mao, Statistical Pattern Recognition: A Review, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.1, p.4-37, January 2000 [doi>10.1109/34.824819]
• 4: Tapas Kanungo , Robert M. Haralick , Werner Stuezle , Henry S. Baird , David Madigan, A Statistical, Nonparametric Methodology for Document Degradation Model Validation, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.11, p.1209-1223, November 2000 [doi>10.1109/34.888707]
• 5: Josep Lladoós , Enric Martí , Juan Josée Villanueva, Symbol Recognition by Error-Tolerant Subgraph Matching between Region Adjacency Graphs, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.23 n.10, p.1137-1143, October 2001 [doi>10.1109/34.954603]
• 6: Bruno T. Messmer , Horst Bunke, Automatic Learning and Recognition of Graphical Symbols in Engineering Drawings, Selected Papers from the First International Workshop on Graphics Recognition, Methods and Applications, p.123-134, August 10-11, 1995
• 7: S. Tabbone , L. Wendling , J.-P. Salmon, A new shape descriptor defined on the radon transform, Computer Vision and Image Understanding, v.102 n.1, p.42-51, April 2006 [doi>10.1016/j.cviu.2005.06.005]
• 8: E. Valveny and P. Dosch. Symbol recognition contest : A synthesis. In Graphics Recognition -- Algorithms and Applications, volume 3088 of lecture notes in computer science. 2004.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION

Keywords:
conditional discriminant analysis, symbol recognition