عنوان مقاله [English]
Weeds normally grow in patches and spatially distributed in field. Patch spraying to control weeds has advantages of reduced cost, chemical saving and environmental pollution. Machine vision system has to obtain and process digital images to make control decisions. Proper identification and classification of weeds holds the key to make control decisions and use of any spraying operation performed. In this study, we develop a robust method based on image processing and computational intelligence for segmentation from other parts of image and classification of weeds. The weeds including large crabgrass, common lambsquarter, velvetleaf, common barnyard grass, European black nightshade, red-rooted pigweed and European heliotrope. The results showed that this algorithm was precisely separated weeds from the soil. In the next step, the feature vector, which includes shape features and color features, was composed. Finally, classification of seven classes of weeds was carried out by artificial neural network (ANN). Among different ANN structures, the 43-15-15-7 topology with accuracy of 88/71 % was the most optimum classifier. The results of this study indicate that the proposed system has the ability to accurately detect weeds.