摘要
针对目前干香菇加工流通环节中分类效率较低,准确度不高等问题,设计了一种基于菌盖开裂纹理特征的干香菇分类方法。首先,对原始数据进行图像阈值处理,将物料前景和背景板进行分离;其次,对阈值处理后的二值化图像进行图像分割,从而分离出每个单独的香菇物料区域;最后,通过对香菇前、后视相机图像的纹理特征进行分析,对香菇物料的品质级别进行量化计算。实验结果表明,该方法能够准确地对干香菇的品级类别做出判断,具有良好的实用价值。
Aiming at the problems of low classification efficiency and low accuracy in the current processing and circulation of dried shiitake mushrooms,a method for classification of dried shiitake mushrooms based on the texture characteristics of cap cracking was designed.First,perform image threshold processing on the original data to separate the material foreground and background plate;second,perform image segmentation on the binarized image to separate each individual mushroom material area;finally,according to the texture analysis of the front and rear view camera images,and the quantitative calculation of the quality factor of the mushroom materials.The experimental results show that the method can accurately judge the grade category of dried shiitake mushrooms and has good practical value.
作者
时宇
孙冬
高清维
卢一相
纪明伟
Shi Yu;Sun Dong;Gao Qingwei;Lu Yixiang;Ji Mingwei(School of Electrical Engineering and Automation,Anhui University,Hefei 230601,China;School of Mechanical and Electrical Engineering,Anhui Jianzhu University,Hefei 230601,China;Hefei Gaojing Optoelectronics Technology Co.,Ltd.,Hefei 230601,China)
出处
《国外电子测量技术》
北大核心
2022年第1期158-162,共5页
Foreign Electronic Measurement Technology
基金
国家自然科学基金(61502007)
安徽省自然科学基金(2008085MF192,2008085MF183)
安徽省教育厅自然科学重点项目(KJ2018A0012,KJ2019A0023,KJ2019A0022)
赛尔网络下一代互联网技术创新项目(NGII20180612,NGII20180312,NGII20180624)资助。
关键词
香菇分类
图像阈值化
纹理特征
品质因数
mushroom classification
image thresholding
texture feature
quality factor
