Agriculture, with its allied sectors, is the largest source of livelihoods in India. Diseases in plants cause a substantial decrease in quality as well as quantity of crops or agricultural products. Detection of these diseases is the solution to prevent losses in the harvest and amount of agricultural products. The main objective of the proposed method is to develop a technique to identify leaf disease in tomato plant by improving the classification accuracy and reducing computational time. The novelty of the work is fusion of multiple features in order to improve classification accuracy. Color histograms, Hu Moments, Haralick and Local Binary Pattern features are used for training and testing purpose. Rrandom forest and decision tree classification algorithms are uses for leaf disease classification. Based on the experiments conducted, it showed that the random forest classifier is more accurate than decision tree classifier. The classification accuracy is 90% for decision tree classifier and 94% for random forest classifier respectively.

农业及其相关部门是印度最大的生计来源。植物中的疾病会导致农作物或农产品的质量以及数量大幅下降。检测这些疾病是防止农产品收成和数量减少的解决方案。该方法的主要目的是开发一种通过提高分类精度和减少计算时间来识别番茄植株叶片病害的技术。这项工作的新颖之处在于融合了多种功能，以提高分类的准确性。颜色直方图，Hu Moments，Haralick和Local Binary Pattern功能用于训练和测试目的。随机森林和决策树分类算法用于叶片疾病分类。根据进行的实验，结果表明，随机森林分类器比决策树分类器更准确。决策树分类器的分类精度为90％，随机森林分类器的分类精度为94％。