Plant Leaf Disease Detection Using an Optimized Evolutionary Gravitational Neocognitron Neural Network

Farming is the strength of a nation in terms of economy and survival of the people. Numerous methodologies based on plant leaf disease detection are developed with deep learning, but it does not precisely categorize the plant leaf disease. This research work introduces a plant leaf disease detection using an optimized evolutionary gravitational neocognitron neural network (EGNNN) for classifying the normal and diseased region of the plant image. Here, the EGNNN is utilized to categorize leaf images with their diseases. The Giza pyramids construction optimization algorithm (GPCOA) is utilized to maximize the accuracy of the network. The introduced approach is implemented in Python programming. The two standard datasets such as plant village datasets and augmented datasets are utilized to evaluate performance of the proposed techniques and achieve 99.92 and 99.98% of accuracy for both datasets. Also, Wilcoxon signed-rank test is performed to demonstrate the effectiveness of the introduced method.