Quantitative Analysis Upon Plant Leaf Diseases Employing Regressive Machine Learning Algorithms

Early detection for plant leaf diseases can be crucial for disease management success and crop loss prevention. In past few years, algorithms according to machine learning have been increasingly utilized in the detection of plant pathogens. The research aimed to compare the effectiveness of two machine learning techniques, two popular algorithms are considered for the evaluation and they are study XG_Boost and LogisticRegression in Early diagnosis of plant leaf ailments. To achieve this, a dataset of leaf images infected with various diseases was used. Color histograms, gray-level co-occurrence matrices, and other image characteristics were obtained to train the machine learning techniques. In order to create training and testing sets, and the algorithms were evaluated according to accuracy, precision, recall, F1-score, and ROC curve. The results indicated that XG_Boost performed better than LogisticRegression in all aspects, with an accuracy of 94.89% for XG_Boost and 79.37% for LogisticRegression.