基于图像信息的马铃薯薯形检测方法研究.PDFVIP

安徽农业大学学报, 2013, 40(5): 883-885 Journal of Anhui Agricultural University 网络出版时间：2013-8-23 9:17:34 [URL] /kcms/detail/34.1162.S0917.023.html 基于图像信息的马铃薯薯形检测方法研究 周 平，徐旭艳，杨 兵，吕 冬，马德贵* (安徽农业大学工学院，合肥 230036) 摘 要：马铃薯按薯形分级是提高其经济价值的重要方法。作者提出了一种基于图像边缘信息的薯形检测方法。 从马铃薯 BMP 图像中提取R 、G 、B 分量，利用 R+G-B 构建灰度图像，经开、闭形态学处理和二值化处理后，运 用 canny 算子检测出边缘点信息；最后利用最大横径与最大纵径的比值作为形状特征参数，建立马铃薯薯形的预测 规则。试验结果表明，该方法可以有效地判断马铃薯薯形，为在线检测马铃薯形状奠定了基础。 关键词：马铃薯；薯形；图像；检测方法 中图分类号：TP391.41 文献标识码：A 文章编号：1672−352X (2013)05−0883−03 Potato shape detection based on image edge information ZHOU Ping, XU Xu-yan, YANG Bin, LV Dong, MA De-gui (School of Engineering, Anhui Agricultural University, Hefei 230036) Abstract: Sorting potato by shape is an important way to improve the economic value of patato. This paper presents an image edge information based detection method. Firstly, the original BMP image was grayed by using the formula of “R+G-B”, and then the gray image was changed into binary image after open and close morphological processing; later, the edge was detected by ‘canny’ module; finally, the maximum transverse diameter (L) and the maximum longitudinal diameter (LD) were defined with the edge information. And the value of L/LD was selected to be the shape characterization parameters. The test results show that this detection method can be effectively applied into potato classification, specifically for online detection of potato shape. Key words: potato; shape; image; detection method 薯形是马铃薯规格等级标准中的重要指标[1] 。 模并检验验证，以期为薯形检测与分级设备研制奠 近年来，国内学者采用计算机视觉技术对此作了不 定理论基础。 少算法研究。2009 年，郑冠楠等采用离心率法将马 铃薯的形状类型分为球型和椭球型两类[2] ，郝敏等 1 材料与方法 人提取了 19个具有旋转不变性的Zernike 矩特征参 1.1 材料 数并输入到支持向量机中，实现了对马铃薯薯形的