# BREADER: A MODULAR FRAMEWORK FOR VISION RECOGNITION OF MATHEMATICAL-LOGICAL STRUCTURES

### Celia Salmim Rafael, Jorge Simao

#### Abstract

We describe a system that uses image processing and computer vision techniques to discover and recognize mathematical, logical, geometric, and other structures and symbols from bit-map images. The system uses a modular architecture to allow easy incorporation of new kinds of object recognizers. The systems uses a ``blackboard'' data-structure to retain the list of objects that have been recognized. Particular object recognizers check this list to discover new objects. Initially, objects are simple pixel clusters resulting from image-processing and segmentation operations. First-level object recognizers include symbol/character recognizers and basic geometric elements. Higher-level object recognizers collect lower-level objects and build more complex objects. This includes mathematical-logical expressions, and complex geometric elements such as polylines, graphs, and others. The recognized objects and structures can be exported to a variety of vector graphic languages and type-setting systems, such as SVG and LaTeX.

#### References

- Blostein, D. and Grbavec, A. (1996). Recognition of mathematical notation.
- C.C. Tappert, C. S. and Wakahara, T. (1990). The state of the art in on-line handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12:787-808.
- Chan, K.-F. and Yeung, D.-Y. (2000). Mathematical expression recognition: a survey. IJDAR, 3(1):3-15.
- Chung, R., Mirica, P., and Plimmer, B. (2005). Inkkit: a generic design tool for the tablet pc. In CHINZ 7805: Proceedings of the 6th ACM SIGCHI New Zealand chapter's international conference on Computerhuman interaction, pages 29-30. ACM.
- Freeman, I. J. and Plimmer, B. (2007). Connector semantics for sketched diagram recognition. In AUIC 7807: Proceedings of the eight Australasian conference on User interface, pages 71-78. Australian Computer Society, Inc.
- Ha, J., Haralick, R., and Phillips, I. (1995). Understanding mathematical expressions from document images. icdar, 02:956.
- Kara, L. B. and Stahovich, T. F. (2004). Hierarchical parsing and recognition of hand-sketched diagrams. In UIST 7804: Proceedings of the 17th annual ACM symposium on User interface software and technology, pages 13-22, New York, NY, USA. ACM.
- Lee, W., Kara, L. B., and Stahovich, T. F. (2007). An efficient graph-based recognizer for hand-drawn symbols. Comput. Graph., 31(4):554-567.
- Li, M.-H. H. X.-D. T. N. (2006). Structural analysis of printed mathematical expressions based on combined strategy. Machine Learning and Cybernetics, 2006 International Conference, pages 3354 - 3358.
- Miller, E. G. and Viola, P. A. (1998). Ambiguity and constraint in mathematical expression recognition. Nat. Conf. on Artif. Intell., pages 784-792.
- Mori, S., Suen, C., , and Yamamoto, K. (1992). Historical review of ocr research and development. Proceedings of the IEEE, 80:1029-1058.
- Nii, P. (1986). Blackboard systems part two: Blackboard application systems. AI Mag., 7(3):82-106.
- Rjean Plamond, S. N. S. (2000). On-line and off-line handwriting recognition: A comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1):63-84.
- Smith, J. (1998). The Book. The publishing company, London, 2nd edition.

#### Paper Citation

#### in Bibtex Style

@conference{visapp09,

author={Celia Salmim Rafael and Jorge Simao},

title={BREADER: A MODULAR FRAMEWORK FOR VISION RECOGNITION OF MATHEMATICAL-LOGICAL STRUCTURES},

booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},

year={2009},

pages={249-255},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0001808702490255},

isbn={978-989-8111-69-2},

}

#### in Harvard Style

Salmim Rafael C. and Simao J. (2009). **BREADER: A MODULAR FRAMEWORK FOR VISION RECOGNITION OF MATHEMATICAL-LOGICAL STRUCTURES** . In *Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)* ISBN 978-989-8111-69-2, pages 249-255. DOI: 10.5220/0001808702490255

#### in EndNote Style

TY - CONF

JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)

TI - BREADER: A MODULAR FRAMEWORK FOR VISION RECOGNITION OF MATHEMATICAL-LOGICAL STRUCTURES

SN - 978-989-8111-69-2

AU - Salmim Rafael C.

AU - Simao J.

PY - 2009

SP - 249

EP - 255

DO - 10.5220/0001808702490255