An Exploratory Analysis of Machine Intelligence-enabled Plant Diseases Assessment

Agriculture plays an important role in India due to population growth and increasing demand for food. Therefore, there is a need to increase crop yields. One of the significant effects of low crop yields is diseases caused by bacteria, fungi and viruses. This can be prevented and controlled by applying plant disease detection approaches. Machine learning techniques are used to identify plant diseases, mainly because they apply the information itself and provide better techniques for detecting plant diseases. Machine learning-based methods apply primarily to data dominance outcomes for specific tasks, and thus can be used to identify diseases. This approach provided a comprehensive overview of various techniques used for plant disease detection using artificial intelligence-based machine learning and deep learning techniques. Similarly, deep learning has become very important in the field of computer vision as it provides better performance results in plant disease detection. Advances in deep learning have been applied to many fields and have brought significant advances in machine learning and computer vision. This comparative study examines machine learning and deep learning techniques, and their performance and use in various research papers aims to show the effectiveness of deep learning and machine learning models. To prevent significant crop loss, leaf disease can be detected using captured images using deep learning techniques. Here we use Kaggle’s PlantVillage dataset for study and analysis.