Agricultural production is improving as a result of recent technological and scientific advances. In agriculture, identifying plant leaf diseases and improving plant leaf quality are critical. There are various laboratory procedures for identifying illnesses, but they are costly and time-consuming for farmers. Polymerase chain response, minimised food cultivation, pest control, and hyper spectral technologies are among them. Agriculture may produce more if machine learning (ML) technology is applied to generate unique, improved procedures and a wide range of systematic models. Researchers focused on how ML algorithms are presently used to diagnose leaf diseases to improve the accuracy of their findings. Each strategy has some potential and focuses on the direction that ML applications travel as well as agricultural challenges. The identification of leaf diseases is addressed in this paper utilising the Support Vector Machine and Random techniques. To supply farmers with more yield in less time and money, performance indicators such as the Root Mean Square Error (RMSE), the Maximum signal - to - interference Relation, the disease-affected part of the foliage by means of the Euclidian technique, and the efficiency of the outcomes are compared.