India's economy relies heavily on agricultural production and is a major source of employment. The early identification of plant leaf diseases is crucial for maximizing revenue and crop productivity. There are more tulsi (Ocimum Tenuiflorum) plant products produced in India than anywhere else in the world. Early methods of observing solely through visual inspection were time-consuming and inaccurate. The present work identifies and categorizes leaf diseases by using a variety of image-processing approaches. The present study demonstrates comprehensive methods for identifying and classifying infections in medicinal plants utilizing image processing and machine learning. The plant village input image dataset having three different types of infected Ocimum Tenuiflorum leaf and healthy leaf is amassed as the basis for this dataset. Through the use of a computer vision lab framework, the image datasets are augmented, pre-processed, segmented, extracted and validated with certain features. Five machine learning classifiers are evaluated using an optimized dataset of infected leaves of Ocimum Tenuiflorum, including logistic regression, linear discriminant analysis, k nearest neighbour, classification and regression trees, random forests, naive bayes, and support vector machines. According to the results, the random forest classifier outperforms the others with an accuracy of 99.86%, followed by the linear discriminant analysis with 98.59%, and the support vector machine with 97.42%.