Smart Agriculture: Plant Disease Detection Using Convolutional Neural Network Method- Survey

Computer Engineering

Deep Learning Models (DLMs) may now be effectively used to produce smart agriculture by pinpointing the disease affected leaf on farms. Convolutional neural networks (CNNs) have consistently outperformed previous technologies in a variety of fields, including agriculture. The primary challenge in computer vision is thought to be semantic picture segmentation. Despite significant advancements in practical, nearly all meaningful picture enhancement algorithms are unable to produce adequate solution due to a lack of details sensitivity, issues determining the same matching, or a combination of the two. The majority of post-processing enhancement techniques rely on Conditional Random Fields, which are a superb vital tool for addressing the fundamental issues with the methods listed above. Identification of plant diseases is therefore important a crucial way in the early detection and illness to lessen its impacts forecast for diseases research objectives in the context. In order to assign disease sections in leaf crops, this study provides an effective approach for identifying plant diseases utilizing meaningful segmentation techniques assessing this network and contrasting it. The findings of the experiment and their comparisons declare regarding disease.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.