An on-line handwritten mathematical equation recognition system that can process matrix expressions by referring to the relative positions of matrix elements

In this paper we describe a method for performing recognition of matrix expressions in an on-line handwritten mathematical equation recognition system. This system incrementally performs recognition of numerical expressions and text input as handwriting and outputs the recognition results as LATEX source code. In previous work we developed the functionality of the system to make it capable of recognizing other two-dimensional structures including subscripts, square root symbols, summation notation, and fractions, but we had not previously been able to deal with matrix structures. We believe that a specialized recognition system is necessary for dealing with matrix structures because they are not expressed using any declarative symbols and involve numerical elements positioned vertically on the page. In this paper we add matrix expression recognition functionality that can be used in real time to the system; this implementation makes use of both geometric features and the relative positions of numerical elements. We performed recognition experiments using the expanded system with input containing matrix expressions and confirmed the effectiveness of the proposed method. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(14): 87–96, 2006; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.10684

[1]  Kensaku Mori,et al.  A Real-Time Recognition Method of Handwritten Math Formulas , 2000 .

[2]  Kensaku Mori,et al.  A new system for the real-time recognition of handwritten mathematical formulas , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[3]  Gerhard Rigoll,et al.  On-line handwritten formula recognition using statistical methods , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[4]  Horst Bunke,et al.  Handbook of Character Recognition and Document Image Analysis , 1997 .

[5]  Dit-Yan Yeung,et al.  PenCalc: a novel application of on-line mathematical expression recognition technology , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[6]  Loïc Pottier,et al.  On-line handwritten formula recognition using hidden Markov models and context dependent graph grammars , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[7]  Masayuki Okamoto,et al.  Performance evaluation of a robust method for mathematical expression recognition , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[8]  Masakazu Suzuki,et al.  Mathematical formula recognition using virtual link network , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[9]  Dit-Yan Yeung,et al.  Mathematical expression recognition: a survey , 2000, International Journal on Document Analysis and Recognition.

[10]  Masakazu Suzuki,et al.  A technique of mathematical expression structure analysis for the handwriting input system , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[11]  Dorothea Blostein,et al.  RECOGNITION OF MATHEMATICAL NOTATION , 1997 .

[12]  C. Faure,et al.  Structural analysis of handwritten mathematical expressions , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[13]  Kanahori Toshihiro,et al.  A Recognition Method of Matrices by Using Variable Block Pattern Elements Generating Rectangular Area , 2001, GREC.

[14]  A. Kosmala,et al.  ON-LINE HANDWRITTEN FORMULA RECOGNITION , 1999 .