Crop and Weed Detection Based on Texture and Size Features and Automatic Spraying of Herbicides

Abstract— Management of Weed is costliest input in the agriculture field. Weed species decreases the growth of the crop and reduce farm yields. Weed competes with crop for sunlight, space and nutrients. To control weed species, a large number of herbicides and chemicals are used in agricultural fields, which results in drinking water contaminated and environmental pollution. Currently, therefore it is important to successfully identify the weeds from the crop to selectively spray herbicides to reduce wastage use of chemical. Wavelet is very popular tool in image processing algorithm. In this paper we developed the image processing algorithm for crop detection and management of weed. Five texture features are used for detection of crop. These five features are energy, entropy, inertia, local homogeneity and contrast. Morphological size based features are also used for detection of crop and weed. Compared the all results and taken majority decision for detection of crop and weed. Image segmentation combines image processing techniques in order to extract cells from the image. The decision making determine the cells to be sprayed. Further the Cartesian robot manipulator is developed to locate the weed position on real field by calculating the coordinates to selectively spray the herbicides. < final year projects >