作　　者： ; ; ; ;

机构地区： 嘉应学院电子信息工程学院

出　　处： 《农机化研究》 2013年第11期22-25,共4页

摘　　要： 介绍了一种基于机器视觉技术的柚子外形尺寸检测系统。利用CMOS摄像头采集柚子正立图像;通过灰度转化、去噪、二值化等预处理获取检测目标图像。通过扫描法确定目标图像的上、下、左、右4个边界点,计算柚子的纵径与横径初测值;借鉴已有的机器视觉球状物体检测误差理论进行修正,获得最终检测结果。试验结果表明,该系统检测精度高且速度快。 A pomelo dimension detection system based on machine vision is introduced.Using CMOS camera to capture upright image of the pomelo,and by gradation conversion,denoising,and binarization preprocessing,the detection target image is obtained.Through scanning method to determine the four boundary points,which is up and down,left and right,the initial value of the longitudinal diameter and transverse diameter of the pamelo is calculated.The initial value is corrected based on the existing detection error theory of spherical object machine vision,and the final test result is obtained.Experimental results show that the detection accuracy is high,and the detection speed is fast.

关 键 词： 机器视觉 柚子 纵径 横径 检测误差

领　　域： [自动化与计算机技术] [自动化与计算机技术]