The Research Of Identifying Field Weed Based On Image Processing Technology

The weed is one of the important factors which affect our country agricultural product quality and output.At present using the herbicide spraying,especially extensive spraying to remove weeds.This kind spraying method not only enhances the agricultural costs,but also undermines the land quality,pollutes the environment,and does not favor the agricultural sustainable development.In response,using computer vision technology to identify weeds and to determine the location and types of weeds was studied in this paper,and it provided theoretical and technical support for accuracy of automated spraying herbicides for the crops field.Main contents are as follows:(1)Introduced the development of weed detection at home and abroad;proposed the research necessity,feasibility and methods.(2)Sutdied the method which used color characteristic of color image to segment green plants and soil background in view of weed detection in complex background.Considered the real time operation,the study used color space and color compents,as a characterization of the image color information threshold parameters.Using iterative threshold segmentation realized the segmentation between the weed area and background area.(3)First of all,in view of the drilling crops,considered the system execution the speed,has first used the position characteristic law recognition between the lines weed.Then,pretreat and threshold on the positioning the weed plant after locating weed,then to do the seed filling,morphological operations,bone extraction and other opertions for the binary image.And then it can get the skeleton tabulate by using the many forks of the traversal algorithm ideas on the skeleton which be extracted.So that it will get the number of the tree leaves.Then I find centroid in the plants of weeds and some marginal points near from the centroid.So I can connect the centroid and the marginal points to separate into some connected blades.(4)As the separated leaves,it can extract the circularity and elongation from each leaf.And then through the images from the separated leaves and the original gray image of weeds after the image by the edge detection,to find the fine edge of each leaf and extract the Hu invariant moment from each leaf.(5)In view of the weed classification,accorading to above extraction,it used the three shape characteristic parameter to take the pattern recognition input eigen vector/feature vector/proper vector,establishes BP neural network.The experimental results showed that the system has good effect effective for weed images. The research of weed identification system had practical significance for suitable applying herbicide,enhancing automatic level of agriculture and protecting environment.