Tomato leaf diseases pose a significant threat to agricultural productivity and food security. Early and precise disease detection minimizes yield losses. This paper proposes an approach for precision classification of tomato leaf diseases using genetic algorithm and K-Nearest Neighbor classifier. Initially, proposed approach extracts morphological, statistical, and textural features from tomato leaf images. Then, a Genetic Algorithm is used for selection of optimal feature subset from extracted feature set, thereby enhancing the classification accuracy of KNN classifier while reducing the number of features. The proposed approach (GA-KNN) is evaluated using Plant Village dataset. The proposed method achieves an accuracy of 94.3% with only 13 features. Obtained results demonstrates the effectiveness of GA-based feature selection for KNN classification in tomato leaf disease identification.