Handwritten Mathematical Equation Solver

Abstract

With recent developments in Artificial intelligence and deep learning every major field which is using computers for any type of work is trying to ease the work using deep learning methods. Deep learning is used in a wide range of fields due to its diverse range of applications like health, sports, robotics, education, etc. In deep learning, a Convolutional neural network (CNN) is being used in image classification, pattern recognition, Text classification, face recognition, live monitoring systems, handwriting recognition, Digit recognition, etc. In this paper, we propose a system for educational use where the recognition and solving process of mathematical equations will be done by machine. In this system for recognition of equations, we use a Convolutional neural network (CNN) model. The proposed system can recognize and solve mathematical equations with basic operations (-,+,/,*) of multiple digits as well as polynomial equations. The model is trained with Modified National Institute of Standards and Technology (MNIST) dataset as well as a manually prepared dataset of operator symbols (“-”,”+”, “/”, “*”, “(“, “)” ). Further, the system uses the RNN model to solve the recognized operations.

An ensemble novel architecture for Bangla Mathematical Entity Recognition (MER) using transformer based learning

“…This approach successfully enhanced the accuracy in this domain on the same dataset, and the accuracy was 76.71%. Shinde et al [28] created an equation solver with CNN on a different dataset MNIST. For complex equations, CNN provided 85% accuracy.…”

Evaluation of Bengali Handwritten Mathematical Equationusing Convolutional Neural Network

“…The system correctly identified 39.11% of something like the formulas in the set of 1000 images, whereas symbol segmentation accuracy reached 91.08%. CNN architecture is used in this formula identification system in the article [23]by Rajwardhan Shinde et al The proposed method recognizes and handles polynomial equations as well as basic operations (-, +, /, *) with many digits. MNIST sample and a manually produced collection of signs ("-","+", "/", "*", "(")) were both utilized to build the model.…”