Research On ARM Based G-SOFM Algorithm And Application

With the development of science and technology, especially the development ofcomputer and digital image technology, many new theories, approaches, algorithms,methods, and techniques come into being. And they are put into practice in respects ofscientific research, agricultural monitoring, and industrial production, etc. They makehuge contributions to social development and are conducive to improve people’s livingstandard. The relevant management of precision agriculture particularly greenhouseagriculture requires the effective collection and extraction of information on cropgrowth. By using the image information，we can control the crop’s growth conditions,collection of fruit, removal of weeds and the spraying of all kinds of nutrients.Based on the shortage of the classification methods in the weed segmentation, theextra-green character segmentation and Self-Organizing Feature Map neural networkwere integrated to develop a G-SOFM space classification model to classify the weedpicture. The method is that using two feature vectors of the gray of excessive green andthe normalized, after the processed of extra-green character segmentation. The resultsshow that by using G-SOFM space classification model classifying better thanextra-green character segmentation method20%. After the algorithm, the imagedenoising method is used, and then the recognition will rate up to94%.The paper also points out that after we get access to the features of images, wecarry out spatial transformation, and then make a feature clustering analysis on thetransformed space. The algorithm improves the clustering effect. Lastly we take afeasibility test in the embedded platform. It turns out that the algorithm is feasible.