Tomato disease condition classification method and device based on artificial neural network

Fecha de publicación: 11/05/2021
Fuente: WIPO "processing tomato"
The invention provides a tomato disease condition classification method and device based on an artificial neural network. The tomato disease condition classification method and device are applied to defect detection in which a CCD camera is adopted to obtain image data. The method comprises the following steps: acquiring an original image of a tomato to be detected, and generating a detection image which contains classification features and corresponds to the tomato to be detected according to the original image; establishing a corresponding relationship between the detection image of the to-be-detected tomato and the symptom classification of the to-be-detected tomato by utilizing the self-learning ability of artificial intelligence; acquiring a current detection image of the current tomato to be detected; and determining the current symptom classification corresponding to the current detection image through the corresponding relation. The obtained original image is preprocessed, so the features of the image are more obvious, and the detection accuracy is improved. And the binary image is used for training the artificial neural network, and the binary image only has a single channel, so that the processing speed is higher than that of RGB image three-channel processing.