Cercospora Identification in Spinach Leaves Through Resnet-50 Based Image Processing

Abstract

Cercospora is a contagious disease that occurs in plant leaves. Spinach is one of the healthiest food that are preferred by the people nowadays. Thus cercospora is the disease that also occurs in the spinach leaves, it also affects the humans. It causes the serious effect in both the spinach plants and also human and animals consuming it. Therefore the usage of image processing and deep learning is done in order to find out the cercospora affected plant and preventing it from the spreading from one plant to the other. To acquire the process of segmentation the plant image feed is given. This process produces an accurate result and as a outcome the cercospora spread can be controlled at the initial stage. This helps farmers to proceeds the decision faster for providing a needed treatment. In proposed system by using the convolutional neural network (CNN) and the Resnet-50 architecture, through which cercospora is identified from the different classes for the spinach leaf disease were detected and classified from the healthy leaves. The result obtained has a greater accuracy in training and testing from a few datasets and thus using this process the identification and the measures can be taken.

Brain cone beam computed tomography image analysis using ResNet50 for collateral circulation classification

“…The pooling procedure is executed by selecting as many elements as possible from the region of filter-covered layer depths. Each layer output in the residual block is passed on to the next layer and hops take place across the identity connections [51].…”

Toward Performing Image Classification and Object Detection With Convolutional Neural Networks in Autonomous Driving Systems: A Survey

“…Domain-general datasets here represent datasets that can be used for the training of CNNs for image classification or object detection, which then could be utilised for a particular application domain. For instance, ResNet-50 [17] has been trained on a domain-general dataset, ImageNet [31], and deployed for image classification tasks in various domains, such as medical [32], agriculture [33], autonomous driving [34], and so on. Contrary to domaingeneral, domain-specific datasets are originally created for a particular domain with the aim to facilitate learning of specialised domain-related features.…”

Bearing Fault Identification Method under Small Samples and Multiple Working Conditions

“…Resnet is a residual network structure stacked by the residual blocks, which has performed well in image classication applications [21,22]. Literature [23] researched the advantage of Resnet-18 by comparing Resnet-18/50, VGG-19, and Googlenet and found that Resnet-18 has the advantages of short training time and high accuracy, developed a deep learning model base on ResNet-18 to diagnose the fan blade surface damage, and got good recognition e ect.…”