基于MATLAB图像处理的苹果大小、颜色、圆形度及缺陷度特征融合分级研究  

Research on Feature Fusion Grading of Apple Size, Color, Roundness and Defect Based on MATLAB Image Processing

作　　者：任龙龙 冯涛 翟传龙 宋月鹏[1,2] REN Long-long;FENG Tao;ZHAI Chuan-long;SONG Yue-peng(School of Mechanical and Electronic Engineering,Shandong Agricultural University,Tai'an Shandong 271018;Shandong Provincial Key Laboratory of Horticultural Machinery and Equipment,Tai'an Shandong 271018)

机构地区：[1]山东农业大学机械与电子工程学院,山东泰安271018 [2]山东省园艺机械与装备重点实验室,山东泰安271018

出　　处：《数字技术与应用》2021年第7期90-95,共6页Digital Technology & Application

基　　金：十三五国家重点研发计划(2018YFD0700604、2016YFD0701701);山东省现代农业产业技术体系果品创新团队专项资金(SDAIT-06-12);山东农业大学“双一流”科技创新团队专项(SYL2017XTTD07);山东省农机装备研发创新计划(2017YF003);山东省自然科学基金(ZR2019MEE092)。

摘　　要：中国是世界苹果生产大国,苹果分级对提高果农收入,加快果品流通具有十分重要的意义。但苹果分级技术及苹果分级装备落后,效率低、精度低,本文利用MATLAB图像处理技术设计了一种苹果分级系统。本系统主要包括四个过程:图像采集,图像预处理,特征提取以及苹果分级。用上述程序进行苹果样本分级实验,与人工分级对比,准确率在75%左右。China is the world's largest producer of apples,and apple grading is of great significance to increase the income of fruit farmers and speed up the circulation of fruit.However,the apple grading technology and the apple grading equipment are backward,with low efficiency and low precision.This article uses MATLAB image processing technology to design an apple grading system.This system mainly includes four processes:image acquisition,image preprocessing,feature extraction and apple grading.Using the above procedure to carry out the grading experiment of apple samples,compared with manual grading,the accuracy rate is about 75%.

关 键 词：苹果分级 MATLAB 图像采集 图像预处理 特征提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]