脐橙表面农药残留的计算机视觉检测方法研究  

The Pesticide Leftover Detection of Navel Orange Using Computer Vision

作　　者：胡淑芬[1] 药林桃[2] 刘木华[1] 

机构地区：[1]江西农业大学工学院,江西南昌330045 [2]江西省农业科学院农业工程研究所,江西南昌330200

出　　处：《江西农业大学学报》2007年第6期1031-1034,共4页Acta Agriculturae Universitatis Jiangxiensis

基　　金：国家自然科学基金资助项目(30460059)

摘　　要：经不同种类农药处理后，采集脐橙激光散射图像，通过对表面是否喷洒农药，以及表面喷洒不同种类农药的水果图像进行处理，用一元非线性方程拟合脐橙图像灰度值分布曲线。结果表明，脐橙图像灰度值在10～100范围内的灰度曲线拟合模型与农药残留是密切相关的，能用于区分脐橙表面是否存在农药残留。The computer vision system was used to detect pesticide leftover on navel orange surface based on laser imaging. A laser spectral imaging system was built for acquisition of laser images of fruit. The image processing and analysis of navel orange were completed to discover the imaging difference among navel orange with different kinds of pesticides on fruit surface. The results showed that the laser imaging technique was good for detection of pesticide leftover on the fruit surface.

关 键 词：计算机视觉 农药残留 曲线拟合 激光图像 脐橙 

分 类 号：TN911.73[电子电信—通信与信息系统] S666.4[电子电信—信息与通信工程]