基于高光谱成像技术的水果表面农药残留无损检测  

Nondestructive detection of pesticide residues on fruit surface by hyperspectral imaging technology

作　　者：张萌[1] 贾世杰[2] ZHANG Meng;JIA Shi-jie(Electrical Engineering Branch,Jilin Railway Vocational and Technical College,Jilin,Jilin 132200,China;School of Electronic Information Engineering,Dalian Jiaotong University,Dalian,Liaoning 116028,China)

机构地区：[1]吉林铁道职业技术学院电气工程分院,吉林吉林132200 [2]大连交通大学电子信息工程学院,辽宁大连116028

出　　处：《食品与机械》2021年第1期99-103,共5页Food and Machinery

基　　金：辽宁省教育厅科学研究项目(编号:JDL2019006)。

摘　　要：在高光谱成像技术的基础上,提出了一种应用于水果表面农药残留的无损检测方法。对采集数据进行预处理和特征提取,通过细菌群体趋药性算法找到最优的最小二乘支持向量机参数,建立农残检测模型,并与最小二乘支持向量机模型进行比较,验证该模型的优越性和准确性。结果表明,基于连续投影法特征波长结合文中检测模型具有最高的检测精度,其准确率达97.92%。Based on the hyperspectral imaging technology,a non-destructive detection method for pesticide residues on fruit surfaces is proposed.By preprocessing the collected data and extract features,finding the optimal least squares support vector machine parameters through the bacterial population chemotaxis algorithm,apesticide residue detection model was established,which was compared with the least squares support vector machine model to verify the superiority and accuracy the model.The results showed that the detection model had the highest detection accuracy based on the characteristic wavelength of the continuous projection method combined with the detection model,and its accuracy rate was 97.92%,which had certain application value.

关 键 词：农药残留 无损检测 高光谱成像技术 细菌群体趋药性算法 最小二乘支持向量机 

分 类 号：S481.8[农业科学—农药学] TP181[农业科学—植物保护] TP391.41[自动化与计算机技术—控制理论与控制工程]