Prediction of Plant Diseases using Simple Novel Image Detection Technique with Improved Accuracy and Compared with Support Vector Machine

Abstract

Aim: The research mainly aims to compare the Simple Novel Image Detection Technique with the Support Vector Machine Algorithm to improve the accuracy of Plant Disease Detection for the purpose of plant protection from unidentified diseases.
Materials and Methods: Machine Learning algorithms based Simple Novel Image Detection Technique (N=50) and Support Vector Machine (N=50) were used for the implementation of the research. The research work uses 100 sample images for testing. The test is calculated using two groups which are done using G power with Pretest Power 0.8. The statistical analysis of two groups is done using SPSS software.
Results: The comparison shows that Simple Novel Image Detection Technique has better mean accuracy of 88.15% when compared with Support Vector Machine where the mean accuracy produced is 75.48% with a significant value of .016 (p<0.05) proves the significance among them.
Conclusion: The results show that the Simple Novel Image Detection technique has better accuracy than the Support Vector Machine algorithm.