[1]班兆军,高喧翔,马肄恒,等.基于高光谱和深度学习的苹果品质无损检测方法[J].江苏农业学报,2024,(08):1446-1454.[doi:doi:10.3969/j.issn.1000-4440.2024.08.009]
　BAN Zhaojun,GAO Xuanxiang,MA Yiheng,et al.Non-destructive detection method of apple quality based on hyperspectral and deep learning[J].,2024,(08):1446-1454.[doi:doi:10.3969/j.issn.1000-4440.2024.08.009]
点击复制

基于高光谱和深度学习的苹果品质无损检测方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年08期
页码:
1446-1454
栏目:
农业信息工程
出版日期:
2024-08-30

文章信息/Info

Title:
Non-destructive detection method of apple quality based on hyperspectral and deep learning
作者:
班兆军1; 高喧翔1; 马肄恒1; 张爽1; 方晨羽1; 王俊博2; 朱艺2
(1.浙江科技学院生物与化学工程学院/浙江省农产品化学与生物加工技术重点实验室/浙江省农业生物资源生化制造协同创新中心,浙江杭州310023；2.阿克苏优能农业科技股份有限公司,新疆阿克苏843100)
Author(s):
BAN Zhaojun1; GAO Xuanxiang1; MA Yiheng1; ZHANG Shuang1; FANG Chenyu1; WANG Junbo2; ZHU Yi2
(1.School of Biological and Chemical Engineering, Zhejiang University of Science and Technology/Zhejiang Provincial Key Laboratory of Chemical and Biological Processing Technology of Farm Products/Zhejiang Provincial Collaborative Innovation Center of Agricultural Biological Resources Biochemical Manufacturing, Hangzhou 310023, China；2.Aksu Youneng Agricultural Technology Co., Ltd., Aksu 843100, China)
关键词:
高光谱; 苹果; 糖酸比; 无损检测
Keywords:
hyperspectral; apple; sugar acid ratio; nondestructive testing
分类号:
S661.1
DOI:
doi:10.3969/j.issn.1000-4440.2024.08.009
文献标志码:
A
摘要:
本研究使用近红外高光谱成像技术获取苹果的高光谱数据,对苹果糖度、酸度指标进行无损检测。针对高光谱数据量大、信息冗余多的特点,分别采用标准化(Standardization,SS)、标准正态变换(Standard normal variate,SNV)、最小二乘平滑滤波(Savitzky-Golay smoothing filtering,SG)和多元散射校正(Multiplicative scatter correction,MSC)对苹果的光谱数据进行预处理。针对高光谱图像波段多的特点,分别采用连续投影(Successive projections algorithm,SPA)算法、竞争性自适应加权重(Competitive adaptive reweighted sampling,CARS)算法和随机蛙跳(Random frog,RF)算法选取苹果的特征波长。对提取的特征波长分别用支持向量机(Support vector machine,SVM)模型、卷积神经网络(Convolutional neural networks,CNN)模型和基于深度学习的定量光谱数据分析(DeepSpectra)模型对苹果的糖酸比进行预测。结果表明,基于深度学习的定量光谱数据分析(DeepSpectra)模型预测的正确率达到93.70%,有较高的精确度,可以较好地对苹果糖酸比进行预测。本研究将高光谱成像技术与基于深度学习的定量光谱数据分析模型相结合,实现了无损检测苹果糖酸比。
Abstract:
The hyperspectral data of apples were obtained by using near-infrared hyperspectral imaging technology, and the indexes of sugar content and acidity were detected nondestructively. For the characteristics of large amount of hyperspectral data and information redundancy, standardization (SS), standard normal variate (SNV), Savitzky-Golay smoothing filtering (SG) and multiplicative scatter correction (MSC) were used to preprocess the spectra of apples. According to the characteristic of hyperspectral images with many bands, successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS) algorithm and random frog (RF) algorithm were used to select the characteristic wavelengths of apples. Support vector machine (SVM) model, convolutional neural networks (CNN) model and quantitative spectral data analysis based on deep learning (DeepSpectra) model were used to predict the sugar-acid ratio of apples. The results showed that the prediction accuracy of DeepSpectra model was 93.70%, which had high accuracy and could be used to predict the sugar-acid ratio of apples. In this study, hyperspectral imaging technology and DeepSpectra model were combined to realize the non-destructive detection of the sugar-acid ratio of apples.

参考文献/References:

[1]彭彦昆,孙晨,赵苗. 苹果品质动态无损感知及分级机器手系统[J]. 农业工程学报,2022,38(16):293-303.
[2]姜宏. 烟台苹果化学成分分析及果实品质的初步评价[D]. 烟台:烟台大学,2014.
[3]孟庆龙,尚静,黄人帅,等. 苹果可溶性固形物的可见/近红外无损检测[J]. 食品与发酵工业,2020,46(16):205-209.

[4]郭志明. 基于近红外光谱及成像的苹果品质无损检测方法和装置研究[D]. 北京:中国农业大学,2015.
[5]樊书祥. 基于可见/近红外光谱及成像技术的苹果可溶性固形物检测研究[D]. 杨凌:西北农林科技大学,2016.
[6]查启明. 基于高光谱成像技术的苹果硬度、水分及可溶性固形物含量的无损检测研究[D]. 南京:南京农业大学,2017.
[7]冯迪. 基于高光谱成像苹果外观与内部多指标检测研究[D]. 沈阳:沈阳农业大学,2017.
[8]SIVAKUMAR S, QIAO J, WANG N, et al. Detecting maturity parameters of mango using hyperspectral imaging technique[C]//ASABE. Annual international meeting of the american society of agricultural and biological engineers. Michigan,USA:ASABE, 2009.
[9]韩如冰. 水果碰伤、糖度和货架期的高光谱成像技术检测[D]. 南昌:华东交通大学,2018.
[10]SANDRA M, CRISTINA B, JOS B, et al. Astringency assessment of persimmon by hyperspectral imaging[J]. Postharvest Biology and Technology,2017,125:35-41.
[11]FERNANDO M, RENFU L, DIWAN A, et al. Integrated spectral and image analysis of hyperspectral scattering data for prediction of apple fruit firmness and soluble solids content[J]. Postharvest Biology and Technology,2011,62(2):149-160.
[12]ACQUARELLI J, VAN LAARHOVEN T, GERRETZEN J, et al. Convolutional neural networks for vibrational spectroscopic data analysis[J]. Analytica Chimica Acta,2017,954:22-31.
[13]张保华,黄文倩,李江波,等. 基于高光谱成像技术和MNF检测苹果的轻微损伤[J]. 光谱学与光谱分析,2014,34(5):1367-1372.
[14]KANDPAL L M, LOHUMI S, KIM M S, et al. Near-in-frared hyperspectral imaging system coupled with multivariate methods to predict viabiliy and vigor in muskmelon seeds[J]. Sensors & Actuators B：Chemical,2016,229:534-544.
[15]袁旭林. 基于高光谱成像技术的苹果糖度无损检测系统研究[D]. 济南:山东大学,2021.
[16]刘燕德,吴明明,孙旭东,等. 黄桃表面缺陷和可溶性固形物光谱同时在线检测[J]. 农业工程学报,2016,32(6):289-295.
[17]张金龙. 基于高光谱成像技术检测柿果货架期的研究[D]. 晋中:山西农业大学,2015.
[18]YANG Q, SUN D W, CHENG W W. Development of simplified models for nondestructive hyperspectral imaging monitoring of TVB-N contents in cured meat during drying process[J]. Journal of Food Engineering,2017,192:53-60.
[19]HE H J, SUN D W. Toward enhancement in prediction of Pseudomonas counts distribution in salmon fillets using NIR hyperspectral imaging[J]. LWT-Food Science and Technology,2015,62(1):11-18.
[20]ARAUJO M C U, SALDANHA T C B, GALVAO R K H, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J]. Chemometrics and Intelligent Laboratory Systems,2001,57(2):65-73.
[21]LI H, LIANG Y, XU Q, et al. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration[J]. Analytica Chimica Acta,2009,648 (1):77-84.
[22]CHEN J Y, LI G H. Prediction of moisture content of wood using Modified Random Frog and VIS-NIR hyperspectral imaging[J]. Infrared Physics & Technology,2020,105:103225.
[23]LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature,2015,521(7553):436-444.
[24]REICHSTEIN M, CAMPSVALLS G, STEVENS B, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature,2019,566(7743):195-204.
[25]BI Y, YUAN K, XIAO W, et al. A local pre-processing method for near-infrared spectra, combined with spectral segmentation and standard normal variate transformation[J]. Analytica Chimica Acta,2016,909:30-40.
[26]王立国,赵亮,刘丹凤. SVM在高光谱图像处理中的应用综述[J]. 哈尔滨工程大学学报,2018,39(6):973-983.
[27]周飞燕,金林鹏,董军. 卷积神经网络研究综述[J]. 计算机学报,2017,40(6):1229-1251.
[28]ZHANG X L, LIN T, XU J F, et al. DeepSpectra:an end-to-end deep learning approach for quantitative spectral analysis[J]. Analytica Chimica Acta,2019,1058:48-57.
[29]SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//IEEE. 2015 IEEE conference on computer vision and pattern recognition (CVPR). Boston,USA:IEEE,2015.
[30]WANG J, WANG J, CHEN Z, et al. Development of multi-cultivar models for predicting the soluble solid content and firmness of European pear (Pyrus communis L.) using portable VIS-NIR spectroscopy[J]. Sensors (Switzerland),2017,129:143-151.
[31]YU X, LU Q. Deep-learning-based regression mode and hyperspectral imaging for rapid detection of nitrogen concentration in oilseed rape (Brassica napuss L.) leaf[J]. Chemometrics and Intelligent Laboratory Systems,2018,172:188-193.
[32]YU K Q, ZHAO Y R,LIU Z Y, et al. Application of visible and near-infrared hyperspectral imaging for detection of defective features in loquat[J]. Food and Bioprocess Technology,2014,7(11):3077-3087.
[33]孙世鹏,彭俊,李瑞,等. 基于近红外高光谱图像的冬枣损伤早期检测[J]. 食品科学,2017,38(2):301-305.
[34]廉孟茹,张淑娟,任锐,等. 基于高光谱技术的鲜食水果玉米含水率无损检测[J]. 食品与机械,2021,37(9):127-132.

相似文献/References:

[1]张丽颖,冯新新,高晶晶,等.根际浇灌ALA 溶液对苹果叶片生理特性与果实品质的影响[J].江苏农业学报,2015,(01):158.[doi:10.3969/j.issn.1000-4440.2015.01.025]
　ZHANG Li-ying,FENG Xin-xin,GAO Jing-jing,et al.Effects of rhizosphere-applied 5-aminolevulinic acid (ALA) solutions on leaf physiological characteristics and fruit quality of apples[J].,2015,(08):158.[doi:10.3969/j.issn.1000-4440.2015.01.025]
[2]刘志刚,徐勤超.基质破碎度对光谱法检测基质含水率的影响[J].江苏农业学报,2017,(05):1051.[doi:doi:10.3969/j.issn.1000-4440.2017.05.014]
　LIU Zhi-gang,XU Qin-chao.Influences of substrate fragmentation degree on substrate water contents detected by hyper-spectral technology[J].,2017,(08):1051.[doi:doi:10.3969/j.issn.1000-4440.2017.05.014]
[3]牛鹏飞,申远,李帅,等.苹果中福美胂残留的RP-HPLC检测[J].江苏农业学报,2018,(03):706.[doi:doi:10.3969/j.issn.1000-4440.2018.03.033]
　NIU Peng-fei,SHEN Yuan,LI Shuai,et al.Determination of residual asomate in apple by reversed-phase high-performance liquid chromatography (RP-HPLC)[J].,2018,(08):706.[doi:doi:10.3969/j.issn.1000-4440.2018.03.033]
[4]王卓卓,何英彬,罗善军,等.基于冠层高光谱数据与马氏距离的马铃薯品种识别[J].江苏农业学报,2018,(05):1036.[doi:doi:10.3969/j.issn.1000-4440.2018.05.010]
　WANG Zhuo-zhuo,HE Ying-bin,LUO Shan-jun,et al.Variety identification of potatoes based on canopy hyperspectral data and Mahalanobis distance[J].,2018,(08):1036.[doi:doi:10.3969/j.issn.1000-4440.2018.05.010]
[5]郑曼迪,熊黑钢,乔娟峰,等.基于综合光谱指数的不同程度人类干扰下土壤有机质含量预测[J].江苏农业学报,2018,(05):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
　ZHENG Man-di,XIONG Hei-gang,QIAO Juan-feng,et al.Prediction of soil organic matter content based on comprehensive spectral index at different levels of human disturbance[J].,2018,(08):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
[6]芦兵,孙俊,毛罕平,等.高光谱和图像特征相融合的生菜病害识别[J].江苏农业学报,2018,(06):1254.[doi:doi:10.3969/j.issn.1000-4440.2018.06.008]
　LU Bing,SUN Jun,MAO Han-ping,et al.Disease recognition of lettuce with feature fusion based on hyperspectrum and image[J].,2018,(08):1254.[doi:doi:10.3969/j.issn.1000-4440.2018.06.008]
[7]车金庆,王帆,王艺洁,等.基于视觉注意机制的黄绿色苹果图像分割[J].江苏农业学报,2018,(06):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
　CHE Jin-qing,WANG Fan,WANG Yi-jie,et al.A segmentation method of yellow and green apple images based on visual attention mechanism[J].,2018,(08):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
[8]车金庆,王帆,吕继东,等.重叠苹果果实的分离识别方法[J].江苏农业学报,2019,(02):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]
　CHE Jin-qing,WANG Fan,LYU Ji-dong,et al.Separation and recognition method for overlapped apple fruits[J].,2019,(08):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]
[9]张永超,赵录怀,王昊,等.基于环境气体信息的BP神经网络苹果贮藏品质预测[J].江苏农业学报,2020,(01):194.[doi:doi:10.3969/j.issn.1000-4440.2020.01.027]
　ZHANG Yong-chao,ZHAO Lu-huai,WANG Hao,et al.Prediction of apple storage quality using BP neural network based on environmental gas information[J].,2020,(08):194.[doi:doi:10.3969/j.issn.1000-4440.2020.01.027]
[10]王婷,刘振华,彭一平,等.华南地区土壤有机质含量高光谱反演[J].江苏农业学报,2020,(02):350.[doi:doi:10.3969/j.issn.1000-4440.2020.02.014]
　WANG Ting,LIU Zhen-hua,PENG Yi-ping,et al.Predicting soil organic matter content in South China based on hyperspectral reflectance[J].,2020,(08):350.[doi:doi:10.3969/j.issn.1000-4440.2020.02.014]

备注/Memo

备注/Memo:
收稿日期：2023-06-21基金项目：浙江省“尖兵”“领雁”重点科技计划项目(2022C04039)作者简介：班兆军(1980-),男,辽宁大石桥人,博士,教授,主要从事农产品采后品质及标准化研究。(E-mail)banzhaojun@zust.edu.cn
更新日期/Last Update: 2024-09-18