Handwritten Mathematical Expression Recognition Using Convolutional Neural Network

Recognizing mathematical expressions on raster images usually consists of two steps: detecting individual symbols and analyzing their spatial structure to form a coherent equation. In this work, we focus on the first step and propose a detection method that is able to locate small and difficult hand...

Full description

Saved in:
Bibliographic Details
Published in2018 3rd International Conference on Control, Robotics and Cybernetics (CRC) pp. 15 - 19
Main Authors Tran, Giang Son, Huynh, Chi-Kien, Le, Thanh-Sach, Phan, Tan-Phuc, Bui, Khanh-Ngoc
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2018
Subjects
Computer science
convolutional neural network
Convolutional neural networks
Handwriting recognition
Image recognition
Layout
mathematical expression recognition
mathematical symbol detection
Training
Urban areas
Online AccessGet full text
DOI10.1109/CRC.2018.00012

Cover

More Information
Summary:Recognizing mathematical expressions on raster images usually consists of two steps: detecting individual symbols and analyzing their spatial structure to form a coherent equation. In this work, we focus on the first step and propose a detection method that is able to locate small and difficult handwritten symbols. We use a deep convolutional neural network with robust detection performance. It is able to achieve a mean average precision score of 0.65 for 106 different mathematical symbols on the dataset we created. For structural analysis, we use the DRACULAE parser since it has high accuracy given that the symbols were correctly detected
DOI:10.1109/CRC.2018.00012