Farmers are increasingly making use of Deep Neural Networks to improve the precision of disease detection in solanaceous crops. To further improve accuracy and simplify disease detection, researchers are comparing Deep Neural Networks’ performance to that of Convolutional Neural Networks. There are five stages to the process of determining which diseases are impacting solanaceous crops. The first step in this procedure is using an image dataset, which is where it all starts. Picture enhancement and segmentation are part of the initial stage of photo pre-processing. The goal of image segmentation is to identify potentially harmful parts and useful parts of the image. The following procedures involve data classification and activities involving feature extraction. This method's end result is the detection of illnesses on solanaceous crops. The present level of accuracy is greatly outstripped by the DNN's 93.4% accuracy, which is especially impressive when contrasted with the CNN's 78.6%. The statistical analysis reveals an unexpected and substantial difference between the two approaches. This analysis's significance value is 0.048, which is lower than the cutoff of 0.05. When it comes to detecting diseases in agricultural crops, deep neural networks (DNNs) outperform convolutional neural networks (CNNs) when it comes to solanaceous crop diseases.