Offline Features for Classifying Handwritten Math Symbols with Recurrent Neural Networks

In mathematical expression recognition, symbol classification is a crucial step. Numerous approaches for recognizing handwritten math symbols have been published, but most of them are either an online approach or a hybrid approach. There is an absence of a study focused on offline features for handwritten math symbol recognition. Furthermore, many papers provide results difficult to compare. In this paper we assess the performance of several well-known offline features for this task. We also test a novel set of features based on polar histograms and the vertical repositioning method for feature extraction. Finally, we report and analyze the results of several experiments using recurrent neural networks on a large public database of online handwritten math expressions. The combination of online and offline features significantly improved the recognition rate.This work was partially supported by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01) and the FPU grant (AP2009-4363), by the Generalitat Valenciana under the grant Prometeo/2009/014, and through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707).Álvaro Muñoz, F.; Sánchez Peiró, JA.; Benedí Ruiz, JM. (2014). Offline Features for Classifying Handwritten Math Symbols with Recurrent Neural Networks. IEEE. https://doi.org/10.1109/ICPR.2014.50