Analysis of Handwritten Equation Recognition System for Comparing Decision Tree and support Vector Machine Algorithm

Abstract

The primary objective of this study is to compare and contrast the performance of the decision tree and support vector machine methods in the context of handwritten equation recognition and to present a fresh approach to this problem. Twenty iterations were performed using a (N=10) for SVM sampling and (N=10) at 80% g-power datasets gathered from a variety of web sources to obtain data in the decision tree technique. For implementation, the additional test will be utilized. Findings indicate that, contrasted with the Decision-making Tree Method (83.8%), the Support Vector Machine approach (91.0%) is more accurate. The statistical significance of the innovative handwritten equation recognition difference of 0.032 (p0.05) indicates that the study's results are statistically significant. The outcomes proved that when it comes to handwritten equation recognition, the support vector machine technique is superior to the decision tree algorithm.