Fecha de publicación: 29/01/2019 Fuente: Wipo tomato The invention provides a method and a device for judging a tomato growth model. The method comprises the following steps of: obtaining an image to be classified of tomato; the images to be classifiedare inputted into the depth convolution neural network model, and the corresponding growth model categories of tomatoes are outputted. Deep convolution neural network model is obtained after trainingon tomato sample image and its corresponding growth model category. The tomato growth model judging method and the tomato growth model judging device provided by the invention obtain tomato images tobe classified, input the tomato images to be classified into a depth convolution neural network model, and output the tomato growth model categories corresponding to the tomato. The invention adopts the depth convolution neural network based on machine learning and depth learning to classify the image, and obtains the growth model category corresponding to the tomato, so that the classification ismore accurate and efficient while increasing the number of training samples.