Neural Networks for Automatic Equation Recognition

This thesis deals with automatic mathematical expressions recognition using deep neural networks. It contains an overview of existing approaches and focuses mainly on handwritten mathematical expressions and the use of graph neural networks. The core of the proposed system for handwritten mathematical expressions recognition is an encoder-decoder neural network model using graph neural networks to exploit the hierarchical structure of mathematical expressions. The designed system is evaluated on the CROHME dataset, which was published within the competition of the same name on mathematical expression recognition. The work also includes description of experiments performed with the designed model. The proposed solution achieves an exact expression recognition rate of 13.34% on the CROHME 2019 test dataset. The contribution of this work is mainly a method of using graph neural networks for mathematical expression recognition from images and their processing in the graph domain