Agriculture plays a significant role in the growth and development
of the economy of any nation. But the emergences of crop-related
diseases affect the productivity [1]. This has not only an impact on
the economy itself, but also influences the security of food supply.
Conventional methods of pest control are mostly controversial and
no longer tolerable for the environment. To cope with these issues
and to implement effective strategies to prevent the propagation of
diseases, crop disease diagnosis with artificial methods is required.
Commonly used techniques are k-Means clustering, Convolutional
Neural Network CNN, and image processing tasks. In this paper, a
combination of Convolutional Neural Network and autoencoder is
explained, which is referred as Convolutional Encoder Network, to
identify crop disease using crop leaf images.
[Abstract]
Agriculture plays a significant role in the growth and development of the economy of any nation. But the emergences of crop-related diseases affect the productivity [1]. This has not only an impact on the economy itself, but also influences the security of food supply.
Conventional methods of pest control are mostly controversial and no longer tolerable for the environment. To cope with these issues and to implement effective strategies to prevent the propagation of diseases, crop disease diagnosis with artificial methods is required. Commonly used techniques are k-Means clustering, Convolutional Neural Network CNN, and image processing tasks. In this paper, a combination of Convolutional Neural Network and autoencoder is explained, which is referred as Convolutional Encoder Network, to identify crop disease using crop leaf images.
Keywords
Artificial Intelligence, Machine Learning, Deep Learning, Crop disease detection, Convolutional Encoder Network, PlantVillage
Link to PDF: short_paper_walser.pdf