Real-time classification of weeds in organic carrot production using deep learning algorithms

This paper proposes a real-time machine learning approach for carrot plants classification in organic farming using Convolutional Neural Network. Artificial neural networks become increasingly popular for image processing tasks, e.g. the classification of complex structures in images. The problem is not very often the accuracy of the classification, but the speed of calculation. The core of this paper presents a real-time calculation flow for the neural networks, in which all the individual steps are summarized. It also briefly discusses the used sensors, which are suitable for the Convolutional Neural Network and the pre-processing which extracts the plants from the background in order to keep the load on the neural network as low as possible.