Tomato Spotted Wilt Disease Severity Levels Detection: A Deep Learning Methodology

Salonki, Vikas; Baliyan, Anupam; Kukreja, Vinay; Siddiqui, Khadim Moin

doi:10.1109/spin52536.2021.9566053

Cited by 41 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pretrained Alex Net model has been loaded into CNN model. After getting the input features of the classifier from the pretrained model, the pretrained head is replaced with a new one [21]- [23]. The new trainable layers are added, and these layers are trained on the input dataset provided so that the model can decide the features to classify different sorts of plant diseases The model is then fine-tuned and the relative weights are saved.…”

Section: Classification Of Images Using Faster Cnnmentioning

confidence: 99%

“…The feature maps generated by the kernel are taken as input by the RPN and outputs two convolution layers. One of the layers provides bounding box regressor outputs which predicts the scales to apply over the anchors and improve predictions [21]. The other layer gives classification outputs as the probability of bounding boxes belonging whether to the background or foreground.…”

Section: • Convolutional Layermentioning

confidence: 99%

“…Having different sizes of regions result in different feature maps. RoI pooling reduces all the feature maps into same size [21], [26], [29]. The input feature map is divided into n number of equal regions and Max-Pooling is applied over the divided regions which results in same number of n despite the variation in size of input.…”

Section: • Convolutional Layermentioning

confidence: 99%

See 2 more Smart Citations

Plant Disease Classification using Alex Net

Kewat¹

2023

Preprint

View full text Add to dashboard Cite

—In modern agriculture field, pest and disease identification is a major role of crop cultivation. Image classification by the use of deep convolutional neural networks of training and methodology used the facilitate a quick and easy system implementation. Pests and diseases are a threat to plant production, especially in India, but identification remains to be a challenge in massive scale and automatically. Collecting images from Image Net dataset. The results show that we can effectively detect and recognize the rice diseases and pests including healthy plant class using a deep convolutional neural network, with the best accuracy of 96.50%. The significantly high success rate makes the model a really useful advisory or early warning tool, and an approach that would be further expanded to support an integrated plant disease identification system to work in real cultivation conditions.

show abstract

Section: Classification Of Images Using Faster Cnnmentioning

confidence: 99%

Section: • Convolutional Layermentioning

confidence: 99%