Abstract: A method for the computer-aided training of an artificial neural network (ANN) for recognizing structural features on objects, by means of which method identified structural features on objects are recognizable rapidly and reliable. That is achieved by virtue of the fact that a convolutional neural network (CNN) having a multiplicity of neurons is used for the training of an ANN for feature recognition on objects. Said network comprises a multiplicity of convolutional and/or pooling layers for the extraction of information from images of individual objects. In this case, the images of the objects are respectively scaled or scaled up and/or down from layer to layer. During the scaling of the images information about the structural features of the objects is maintained, specifically independently of the scaling of the images.

Abstract: An apparatus and a method for processing plants includes an apparatus for processing at least one plant has at least one conveyor device for transporting the plant, at least one image recognition device, at least one gripping means for the targeted depositing of the plant on the conveyor device, and at least one processing means for processing the plant lying on the conveyor device.

Abstract: A method by means of which the processing of plants can be carried out in a more time- and cost-efficient manner. For this purpose, at least one plant or a component of the plant is detected by an image-recognition device. Using the patterns and features of the plants recognized by the image-recognition device, at least one option for processing the plant is suggested to a person. Upon selection of at least one option by the person, the plant or the component of the plant is autonomously or automatically processed by a processing means.

Abstract: A method for the computer-aided training of an artificial neural network (ANN) for recognizing structural features on objects, by means of which method identified structural features on objects are recognizable rapidly and reliable. That is achieved by virtue of the fact that a convolutional neural network (CNN) having a multiplicity of neurons is used for the training of an ANN for feature recognition on objects. Said network comprises a multiplicity of convolutional and/or pooling layers for the extraction of information from images of individual objects. In this case, the images of the objects are respectively scaled or scaled up and/or down from layer to layer. During the scaling of the images information about the structural features of the objects is maintained, specifically independently of the scaling of the images.