Name
Abstract | ||
|---|---|---|
The timely identification of plant diseases prevents the negative impact on crops. Convolutional neural network, particularly deep learning is used widely in machine vision and pattern recognition task. Researchers proposed different deep learning models in the identification of diseases in plants. However, the deep learning models require a large number of parameters, and hence the required training time is more and also difficult to implement on small devices. In this paper, we have proposed a novel deep learning model based on the inception layer and residual connection. Depthwise separable convolution is used to reduce the number of parameters. The proposed model has been trained and tested on three different plant diseases datasets. The performance accuracy obtained on plantvillage dataset is 99.39%, on the rice disease dataset is 99.66%, and on the cassava dataset is 76.59%. With fewer number of parameters, the proposed model achieves higher accuracy in comparison with the state-of-art deep learning models. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/ACCESS.2022.3141371 | IEEE ACCESS |
Keywords | DocType | Volume |
Diseases, Convolution, Deep learning, Feature extraction, Convolutional neural networks, Computational modeling, Standards, Plant disease, machine learning, deep learning, depthwise convolution, pointwise convolution | Journal | 10 |
ISSN | Citations | PageRank |
2169-3536 | 0 | 0.34 |
References | Authors | |
0 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sk Mahmudul Hassan | 1 | 0 | 0.34 |
| Arnab Kumar Maji | 2 | 0 | 0.34 |