Comparison and Analysis of CNN Based Algorithms for Plant Disease Identification

High crop yield is an important feature that impacts the field of agribusiness and farmers financially and socially from every perspective. At different stages of a crop's growth, it is important to keep a close eye on it so that early infections can be found. Manual examination of the crops cannot help because humans are always prone to errors, the risk of false predictions is high, and it is very time-consuming as well. Also, when the paradigm shift is towards smart agriculture these years, automation of every aspect of crop growing and monitoring is important. Therefore, in this work, we have analyzed the appropriateness of an automated approach for the classification of diseases in plants. In this study, two algorithms, one based on a CNN and the other on a VGG-16 approach, have been compared and analyzed in terms of accuracy and loss. The performance has been verified with the plant village dataset, and the accuracy given by the first trained model of CNN (convolutional neural network) was 96.77%, and the VGG16-based trained model with batch normalization gives an accuracy of 94%.