Context-based Multi-stage Offline Handwritten Mathematical Symbol Recognition using Deep Learning

Abstract

We propose a multi-stage machine learning (ML) architecture to improve the accuracy of offline handwritten mathematical symbol recognition. In the first stage, we train and assemble multiple deep convolutional neural networks to classify isolated mathematical symbols. However, certain ambiguous symbols are hard to classify without the context information of the mathematical expressions where the symbols belong. In the second stage, we train a deep convolutional neural network that further classifies the ambiguous symbols based on the context information of the symbols. To further improve the classification accuracy, in the third stage, we develop a set of rules to classify the ambiguity or otherwise the syntax of the mathematical expressions will be violated. We evaluate the proposed method by using the Competition on Recognition of Online Handwritten Mathematical Expressions (CROHME) dataset. The proposed method results the state-of-the-art accuracy of 94.04%, which is 1.62% improvement compared with the previous single-stage approach.