COMPUTER VISION SYSTEM FOR ONLINE SORTING OF POT PLANTS USING AN ARTIFICIAL NEURAL-NETWORK CLASSIFIER

A flexible grading system for pot plants is described. The system cons ists of a colour camera, an image processing system and specially deve loped software. It can be applied to several types of pot plants becau se of its implementation of learning techniques. Experiments are descr ibed for classification of a flowered plant and a cactus plant. Statis tical discriminant analysis and a neural network (NN) classifier are u sed as techniques for pattern recognition. NNs gave for less complex a pplications at least equal results as linear discriminant analysis (LD A) or quadratic discriminant analysis (QDA). For more complex applicat ions the NN classifier showed better results. Complexity for the descr ibed classification tasks can be associated with the distribution and shape of groups in the multi-dimensional feature space.