This research introduces a novel enhanced deep convolutional neural network for plant disease detection and classification, a cutting-edge tool that is set to revolutionize the field. The study enhances the ResNet50 network by replacing the fully connected layer with three layers that improve discrimination and feature extraction, namely the convolution, batch normalization, and Leaky rectified linear unit (RELU) activation layers. Experimental performance assessments were conducted to evaluate the performance of the proposed model in comparison to the original ResNet50, EfficientNet, DesNet201, and Inception Version 3 using popular evaluation criteria such as precision, recall, and F1-Score. The proposed model achieved an accuracy of 99.33% and 93.93% on the Namibia University of Science and Technology Maize Dataset and the Nelson Mandela African Institution of Science and Technology Maize dataset, respectively.