Symbol recognition using graphs

Symbol recognition is a well-known challenge in the field of graphics recognition. A symbol can be defined as a structure within a document that has a particular meaning in the context of the application. Due to their representational power, graph structures are usually used to represent line drawings images. Thus, a number of graph comparison approaches are required to answer whether a known symbol appears in a document and under which degree of confidence. In this paper we propose two strategies to recognize symbols depending on the type of their substructures. For those symbols that can be defined by a prototype pattern, we propose a graph isomorphism approach. On the other hand, for those structures consisting of repetitive patterns, we propose a syntactic approach based on graph grammars.

[1]  Josep Lladós,et al.  An Error-Correction Graph Grammar to Recognize Texture Symbols , 2001, GREC.

[2]  Michael J. Fischer,et al.  The String-to-String Correction Problem , 1974, JACM.

[3]  Birgit Ueberreiter,et al.  Pattern Recognition by Graph Matching - Combinatorial versus continuous Optimization , 1988, Int. J. Pattern Recognit. Artif. Intell..

[4]  Dov Dori,et al.  A syntactic/geometric approach to recognition of dimensions in engineering machine drawings , 1989, Comput. Vis. Graph. Image Process..

[5]  Josep Lladós,et al.  A mean string algorithm to compute the average among a set of 2D shapes , 2002, Pattern Recognit. Lett..

[6]  Horst Bunke,et al.  Automatic Learning and Recognition of Graphical Symbols in Engineering Drawings , 1995, GREC.

[7]  Kaizhong Zhang,et al.  The approximate graph matching problem , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[8]  Dorothea Blostein,et al.  A graph grammar programming style for recognition of music notation , 1993, Machine Vision and Applications.

[9]  Christian Ah-Soon,et al.  Architectural symbol recognition using a network of constraints , 2001, Pattern Recognit. Lett..

[10]  Horst Bunke,et al.  Synthesis of Representative Graphical Symbols by Computing Generalized Median Graph , 1999, GREC.

[11]  Josep Lladós,et al.  Symbol Recognition by Error-Tolerant Subgraph Matching between Region Adjacency Graphs , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Horst Bunke.  Attributed Programmed Graph Grammars and Their Application to Schematic Diagram Interpretation , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Stephane Lavirotte.  Optical formula recognition , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.