Journal of Computer Engineering & Information TechnologyISSN : 2324-9307

Research Article, J Regen Med Vol: 7 Issue: 1

Back Propagation Neural Network (BPNN) Based Recognition Of Handwritten Mathematical Equations

Sagar Shinde1* and Rajendra Waghulade2

1JSPM, Narhe Technical Campus, Savitribai Phule Pune University, India

2DNCVP, North Maharashtra University, India

*Corresponding Author : Sagar Shinde
Assistant Professor, Udaipur and JSPM, Narhe Technical Campus, Savitribai Phule Pune University, Maharashtra, India
E-mail: [email protected]

Received: May 29, 2018 Accepted: June 08, 2018 Published: June 15, 2018

Citation: Shinde S, Waghulade R (2018) Back Propagation Neural Network (BPNN) Based Recognition of Handwritten Mathematical Equations. J Comput Eng Inf Technol 7:1. doi: 10.4172/2324-9307.1000192

Abstract

The recognition of handwritten mathematical symbols and equations are the critical and challenging issue in the field of pattern recognition. The machine learning approach with multilayer perceptron feed forward back propagation neural network algorithm with an offline mode of recognition has been used to improve throughput and accuracy. The hybrid feature extracted viz. centroid, boundary box, zoning density etc and gradient descent with momentum training algorithm has been used. Adaptive learning is used to carry out the experiment on numerous kinds of equations. An experimental result shows the significant improvement in recognition of simple as well as complicated mathematical equations. In future current methodology will be the key factor to initiate paperless work and digital world.

Keywords: Math symbols and equations; Hybrid feature; Back propagation neural network; Adaptive learning; 2-D layout; Throughput; Accuracy

Track Your Manuscript

Share This Page