Conclusion

Agriculture plays a significant role in improving the economic condition of any country. The crop growth is reduced due to weeds. Earlier the weeds were detected manually, however it is a very expensive and time consuming process. Currently, weed detection is done by robotics, automatic sprayer and weed cutting are thus used. This kind of robotics works based upon sensors, image processing and machine learning algorithms were embedded within hardware devices. This chapter proposes image processing and machine learning algorithms used to identify weeds from plants. The proposed algorithm classifies the weed and plants from the soil and then GLCM features are selected from segmented images. These features are applied in SVM and neural network machine learning algorithms which helps to differentiate the weed from plants accurately using bounding boxes. This automatic algorithm helps the smart agricultural field to detect the weed area in its early stage automatically and thus reduces the manual work and excess use of herbicides.