Plant diseases, caused by infectious organisms and unfavorable environmental conditions, pose a significant threat to agriculture. These diseases lead to notable decreases in crop yields, resulting in substantial economic losses. It is essential to address these challenges and safeguard the food supply and sustain effective farming practices. Though the detection of diseases in plants and crops through the traditional methods has always been a very difficult task to deal with the emergence of the AI (artificial intelligence) technologies has enhanced the efficiency and the accuracy of the diagnosis. This study presents a brief overview of the various machine and deep learning methods used for disease recognition in plants and compares the performance of the machine learning and deep learning algorithms in the detection of diseases in plants. The comparative study demonstrates that the deep learning methods achieve higher accuracy and better performance on complex tasks related to machine learning at the cost of increased computational resources and training time.

Disease detection Machine Learning Deep Learning Naïve Bayes KNN CNN RNN