麦田杂草的图像识别技术的研究

Research of the Identification of Weed Images in Wheat Fields

主要研究了麦田杂草的图像识别技术,设计了麦田杂草识别系统。该系统包括使用数码相机进行麦田图像数据的采集,实现对图像的预处理;绿色植物与土壤背景的分割包括图像的灰度化与格式转换和图像的二值化;作物与杂草的分割包括作物中心行的识别和作物行的滤除,最后获取杂草图像。在滤除作物行的过程中确定边界阈值时采用通过先计算手工标定的作物行宽度与计算机自动检测的作物行宽度之间的相对误差,然后选定合适的对应最小误差的作物行边界阈值的方法。该系统全程使用MATLAB语言编程,系统最终目的是根据杂草和作物分布的位置特征滤除作物行,识别出杂草。

This paper studies the identification technology of weed images in wheat fields and designs the system of identification of weed images in wheat fields. The major content includes collecting images using digital camera; retreating images; partitioning the green plants and the soil which includes again transforming the color images into grey images, and transforming the images＇ formats, and transforming the grey images into binary images; partitioning the crop and the weed which includes again the identification of the center line of the crop and filtering of the crop line; finally obtaining the weed images. In order to compute the boundary of crop line, we Choose different thresholds to compute the relative error between the automatically detected crop line width and the manually defined crop line width, and we finally choose the appropriate threshold that minimum error. The system programs with MATLAB language. So the system can successfully filter out the crop lines and identify the weed by the location characteristics of distribution of the crop lines and the weed.