Paper Info
Title
Recognition of Spatial Relations in Mathematical Formulas
Abstract
A critical issue in recognition of mathematical expressions is the identification of the spatial relations of the symbols or/and sub-expressions that comprise the entire mathematical formula. This paper addresses the problem of structural analysis of mathematical expressions by constructing appropriate feature vectors to represent the spatial affinity of the objects (mathematical symbols or sub-expressions) under examination and employing two popular machine learning techniques: (i) Support Vector Machines (SVM) and (ii) Artificial Neural Networks (ANN) to recognize the spatial relation between these objects. In order to evaluate the proposed techniques, we use Math Brush, a large publicly available dataset of mathematical expressions with annotated spatial relations, and a subset of spatial relations derived from the mathematical expressions the CROHME 2012 dataset. The experimental results give an overall mean error rate of 2.8% for the SVM and 3.4% for the ANN classifiers respectively, which are at par with other approaches evaluated on the same datasets.
Year
DOI
Venue
2014
10.1109/ICFHR.2014.35
Frontiers in Handwriting Recognition
Keywords
DocType
ISSN
document image processing,handwriting recognition,mathematics computing,neural nets,object recognition,support vector machines,ANN classifier,Math Brush,SVM,artificial neural network,feature vector,machine learning,mathematical expression recognition,mathematical formula,mean error rate,spatial relation recognition,support vector machine,artificial neural networks,handwritten mathematical expressions,spatial relations of mathematical symbols,structural analysis of handwritten mathematical expressions,support vector machines
Conference
2167-6445
Citations 
PageRank 
References 
2
0.41
8
Authors
4
Name
Order
Citations
PageRank
Fotini Simistira1244.04
Vassilis Papavassiliou212010.74
Vassilios Katsouros37310.63
George Carayannis421538.14