In order to solve the problems of conventional neural network when it is applied to the diseased plant leaf system such as making itself for better classification, Genetic algorithm-based feed forward neural network (GA_FFNN) hybrid technique is proposed. Besides, Particle swarm optimization (PSO)-based segmented hybrid features were used for the analysis of classification of diseased leaf and its severity. The main contribution of this paper incorporates Genetic weight optimization-based neural network systems of diseased plant leaf classification for better classification accuracy. Various diseased plant leaves such as bitter gourd (Brown Leaf Spot), beans (Pest leaf minor), chilly (Pest), Cotton (Mineral Deficiency), pigeon pea (Blight Leaf minor) and tomato (Leaf spot) were used. In the proposed work, attributes are combined as a single vector for hybrid features. Five attributes, namely contrast, correlation, energy, homogeneity and area of the leaf were used as features. Initially, the features were extracted from the segmented image after preprocessing. Genetic-based Feed Forward Neural network architecture is constructed for the classification of diseased plant leaf. The weight of the neural network is updated by Genetic algorithm for specified iterations. Finally, the performance is analyzed in different classes (class 2, class 3 and class 6) of diseased plant leaves using classification accuracy.