基于图像处理和支持向量机的粉碎性秸秆覆盖率的图像识别方法研究  

Research on Image Recognition Method Based on SVM Algorithm and ESN Algorithm for Crushed Straw Mulching Rate

作　　者：于国庆[1] 郝若帆 马洪涛[1] 吴赛敏 陈梦雅 YU Guoqing;HAO Ruofan;MA Hongtao;WU Saimin;CHEN Mengya(School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,China)

机构地区：[1]河北科技大学信息科学与工程学院,河北石家庄050018

出　　处：《河南农业科学》2018年第11期155-160,共6页Journal of Henan Agricultural Sciences

基　　金：国家科技部项目(14C26211300460)

摘　　要：针对秸秆还田后的秸秆细碎、在自然光照下与土壤颜色差别很小导致秸秆覆盖率检测精度低的问题,提出了一种基于灰度变换函数与支持向量机(SVM)算法相结合的秸秆覆盖率图像识别方法。首先对在自然光下拍照获取的粉碎秸秆的彩色图像进行灰度变换处理,然后应用SVM算法对其进行秸秆图像分类,最后应用形态学图像处理算法得到准确的图像覆盖率。结果表明,对5个不同地块的秸秆图像进行灰度变换处理后,利用SVM训练文件直接预测得到的秸秆覆盖率与田间实际测量结果的最大误差率为3.20%,最小误差率为1.00%,分类时间小于2 s。可见,采用此方法检测粉碎秸秆的还田覆盖率具有很好的识别效果,并且用经过训练后的结果对所有图像进行SVM预测,不受光照的影响,效率高,分类速度快。Aiming at solving the problem of low detection accuracy of the straw coverage rate that caused by finely shredding of straws after returning to the field and the small color difference between the straw and the soil under natural light,a straw coverage image recognition method based on gray transform function and support vector machine(SVM)algorithm was proposed.Firstly,the color image of crushed straw was photographed in natural light and processed by gray transformation,then SVM algorithm was used to classify the straw images,finally,morphological image processing algorithm was applied to get the accurate image coverage.The results showed that after gray transform processing of the straw images of five different plots,the maximum error rate between the straw coverage predicted by SVM training file and the measured results in field was 3.20%,the minimum error rate was 1.00%,and the classification time was less than 2 s.Taken together,this method had a good recognition effect on the field coverage of crushed straw,and the SVM prediction could be performed on all the images using the trained results with high efficiency and fast classification,which was not affected by the illumination.

关 键 词：秸秆覆盖率 图像识别 SVM(支持向量机) 灰度变换处理 形态学图像处理 

分 类 号：S126[农业科学—农业基础科学]