Recognition of online handwritten mathematical formulas using probabilistic SVMs and stochastic context free grammars

• Method to recognize spatial relations between mathematical objects in equations.
• A CYK-based algorithm on a 2D SCFG for recognizing mathematical expressions.
• Evaluation of the proposed methods on MathBrush and CROHME datasets.

Although recognition of online handwritten text has reached a point of maturity, recognition of online handwritten mathematical expressions remains still a challenging problem. In this work we train a probabilistic SVM classifier to recognize spatial relations between two mathematical symbols or sub-expressions and then employ a CYK based algorithm to parse the mathematical expression in order to produce the respective MathML output. For the recognition of mathematical expressions we assume compliance with a stochastic context free grammar. It must be noted that in this work we make the assumption that the symbols that comprise the mathematical expression have been correctly recognized. We evaluate the recognition of spatial relation on the MathBrush database and the experimental results produce an overall mean error rate of 2.8%. MathML output is evaluated with the use of the datasets and evaluation tools of the CROHME2012 and CROHME2013 competitions. Experimental results give, at mathematical expression level, an accuracy of 78.70%, 65.78%, 56.37% and 50.22% for the Part-I, Part-II, Part-III and Part-IV on the respective test sets.

Figure optionsDownload high-quality image (82 K)Download as PowerPoint slide