Infection Segmentation of Leaves Using Deep Learning techniques to enhance crop productivity in smart agriculture

Agriculture has been playing a vital role in human existence. Several new techniques have been invented and discovered to increase crop productivity. Along with the increase in crop production, the problems related to disease/infection in the crop have also increased. The farmer may sometimes have low or no knowledge about the infection, or he may be in a situation where he couldn’t be able to identify the small traces of the infection that has been induced on the leaves. Infection classification, detection, and segmentation play a vital role in helping the farmers identify the infection at its budding stage and take the required remedies for it. The previous approaches made in this context were based on classification and detection only. These approaches have certain limitations, and they did not specify the infection in its exact proportion. To overcome the limitations of previous approaches, a segmentation approach can be used to accurately segment all infected spots of the infection on the leaves in their exact shape. Instance segmentation of the leaf disease helps to solve the overlapping bounding boxes problem as it segments the infected spots with different colors showing the difference. The advantage of segmentation further covers the classification of the infection type, localizing with the help of a bounding box, and essentially segment the infected areas using colored masks. Mask RCNN, is the instance segmentation algorithm that can be used to solve the aforementioned problem, by processing through several layers of convolutional neural networks. Instance Segmentation is difficult because it necessitates both accurate detections of all objects in an image and exact segmentation of each instance. This helps the farmer identify the infection on the leaf without prior knowledge about the type of infection that has affected the crop to take the required remedy to stop the infection. Moreover, this approach eliminates the burden of manual intervention in identifying the infection.