光谱成像技术在玉米种子质量检测方面的研究进展

doi:10.12190/j.issn.2096-1197.2023.05.10

摘要/Abstract

摘要：

应用传统检测技术检测种子质量难以满足快速、无损、高效的要求。随着科技的进步，通过光谱成像技术结合化学计量学方法获取被测物的光谱信息和图像信息，具有快速、无损害、高效率等优点，目前该方法应用到种子质量检测技术的各个方面。文章介绍了光谱成像技术原理，归纳了光谱成像技术检测流程中的玉米种子状态、光谱数据预处理方法、光谱数据特征波长提取方法、建模分析方法和模型评价指标，并总结了光谱成像技术在玉米种子活力、水分、病害、品质与产地等方面检测的研究进展，最后结合光谱成像技术在玉米种子质量检测中存在的数据处理效率低、模型准确率低等问题，从研究系统化、融合新算法等方面展望了光谱成像技术的发展趋势，以期为玉米种子无损检测提供参考。

关键词: 玉米种子, 光谱成像技术, 质量, 检测

Abstract:

Using traditional detection technology to meet the requirements of rapid，non-destructive，and effective seed quality detection is challenging. As science and technology advance，spectral imaging technology in conjunction with chemometric methods is now able to get both the spectral and image information of the analyte，offering the benefits of speed，non-destructiveness，and high efficiency. The method is currently applied to all aspects of seed quality detection technology. This paper introduced the theory of spectral imaging technology，summarized the status of maize seeds，the method of spectral data preprocessing，the method of extracting the characteristic wavelength of spectral data，the modeling analysis method and the model evaluation index in the detection process of spectral imaging technology. It also reviewed the research progress of spectral imaging technology in detecting maize seed vitality，moisture，disease，quality and origin. In the end，considering the problems of low data processing efficiency and low model accuracy in the quality detection of maize seeds using spectral imaging technology，the development trend of spectral imaging technology was prospected from the perspectives of research systematization and fusion of new algorithms，in order to provide references for non-destructive testing of maize seeds.

Key words: Maize seeds, Spectral imaging technology, Quality, Detection

中图分类号:

S339.31

靖相柱, 孙霞, 郭业民, 赵文苹, 郭榛, 桑茂盛. 光谱成像技术在玉米种子质量检测方面的研究进展[J]. 北方农业学报, 2023, 51(5): 93-102.

JING Xiangzhu, SUN Xia, GUO Yemin, ZHAO Wenping, GUO Zhen, SANG Maosheng. Research progress of spectral imaging technology in maize seed quality detection[J]. Journal of Northern Agriculture, 2023, 51(5): 93-102.

图/表 3

参考文献 52

[1]	张伏, 张朝臣, 陈自均, 等. 光谱检测技术在种子质量检测中的应用[J]. 中国农机化学报, 2021, 42(2):109-114. doi: 10.13733/j.jcam.issn.2095-5553.2021.02.016
[2]	杨小倩, 郅慧, 张辉, 等. 玉米不同部位化学成分、药理作用、利用现状研究进展[J]. 吉林中医药, 2019, 39(6):837-840.
[3]	周迎鑫, 李玥峤, 吕庆雪, 等. 玉米子粒主要营养成分合成调控研究进展[J]. 玉米科学, 2023, 31(2):59-66.
[4]	REN X G, TIAN H Q, ZHAO K, et al. Research on pH value detection method during maize silage secondary fermentation based on computer vision[J]. Agriculture, 2022, 12(10):1623. doi: 10.3390/agriculture12101623
[5]	KANG Z, HUANG T C, ZENG S, et al. A method for detection of corn kernel mildew based on co-clustering algorithm with hyperspectral image technology[J]. Sensors, 2022, 22(14):5333. doi: 10.3390/s22145333
[6]	程锦锋, 方贵盛, 高惠芳. 表面缺陷检测的机器视觉技术研究进展[J]. 计算机应用研究, 2023, 40(4):967-977.
[7]	王建伟, 陶飞, 郭双欢, 等. 近红外光谱技术在食品安全检测中的应用进展[J]. 食品工业, 2021, 42(12):461-464.
[8]	MISHRA G, PANDA B K, RAMIREZ W A, et al. Research advancements in optical imaging and spectroscopic techniques for nondestructive detection of mold infection and mycotoxins in cereal grains and nuts[J]. Comprehensive Reviews in Food Science and Food Safety, 2021, 20(5):4612-4651. doi: 10.1111/1541-4337.12801 pmid: 34338431
[9]	TU K L, WEN S Z, CHENG Y, et al. A non-destructive and highly efficient model for detecting the genuineness of maize variety“INGKE 968” using machine vision combined with deep learning[J]. Computers and Electronics in Agriculture, 2021, 182:106002. doi: 10.1016/j.compag.2021.106002
[10]	ALTUNTA Y, CÖMERT Z, KOCAMAZ A F. Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approach[J]. Computers and Electronics in Agriculture, 2019, 163:104874. doi: 10.1016/j.compag.2019.104874
[11]	冯晓, 张辉, 周蕊, 等. 基于深度学习和籽粒双面特征的玉米品种识别[J]. 系统仿真学报, 2021, 33(12):2983-2991. doi: 10.16182/j.issn1004731x.joss.21-FZ0771
[12]	FAN Y M, MA S C, WU T T. Individual wheat kernels vigor assessment based on NIR spectroscopy coupled with machine learning methodologies[J]. Infrared Physics and Technology, 2020, 105:103213. doi: 10.1016/j.infrared.2020.103213
[13]	熊春晖, 佘永新, 焦逊, 等. 高光谱成像技术在农产品无损检测中的应用[J]. 粮油食品科技, 2023, 31(1):109-122.
[14]	RIEFOLO C, ANTELMI I, CASTRIGNANO A, et al. Assessment of the hyperspectral data analysis as a tool to diagnose Xylella fastidiosa in the asymptomatic leaves of olive plants[J]. Plants, 2021, 10(4):683. doi: 10.3390/plants10040683
[15]	MANGANIELLO G, NICASTRO N, CAPUTO M, et al. Functional hyperspectral imaging by high-related vegetation indices to track the wide-spectrum Trichoderma biocontrol activity against soil-borne diseases of baby-leaf vegetables[J]. Frontiers in Plant Science, 2021, 12:630059. doi: 10.3389/fpls.2021.630059
[16]	张瀚文, 李野, 江晟, 等. 近红外高光谱大米典型特征提取分类识别[J]. 吉林大学学报(理学版), 2022, 60(3):655-663.
[17]	黄锋华, 燕红文, 苗荣慧. 高光谱技术结合GLCM的油桃品种判别研究[J]. 农业技术与装备, 2021(12):5-7.
[18]	郑守国, 翁士状, 刘瑜凡, 等. 融合高光谱成像多类特征的名优牛肉种类鉴别[J]. 激光杂志, 2021, 42(8):57-61.
[19]	李士静, 潘羲, 陈熙卓, 等. 基于高光谱信息的烟叶分级方法比较[J]. 烟草科技, 2021, 54(10):82-91.
[20]	郭榛, 金诚谦, 刘鹏. 光谱分析和光谱成像技术检测大豆品质的研究进展[J]. 大豆科学, 2022, 41(1):99-106.
[21]	GOETZ A F H, VANE G, SOLOMON J E, et al. Imaging spectrometry for earth remote sensing[J]. Science, 1985, 228(4704):1147-1153. doi: 10.1126/science.228.4704.1147 pmid: 17735325
[22]	王建宇, 李春来. 高光谱遥感成像技术的发展与展望[J]. 空间科学学报, 2021, 41(1):22-33.
[23]	崔莹莹, 杨铭铎, 方伟佳, 等. 高光谱成像技术在红肉食用品质检测中的应用研究进展[J]. 肉类研究, 2019, 33(6):70-76.
[24]	孙建非. 基于高光谱成像技术的花生多项品质参数无损检测方法的研究[D]. 淄博: 山东理工大学, 2020.
[25]	ARIANA D P, LU R. Quality evaluation of pickling cucumbers using hyperspectral reflectance and transmittance imaging:Part Ⅰ. Development of a prototype[J]. Sensing and Instrumentation for Food Quality and Safety, 2008, 2:144-151. doi: 10.1007/s11694-008-9057-x
[26]	刘欢, 王雅倩, 王晓明, 等. 基于近红外高光谱成像技术的小麦不完善粒检测方法研究[J]. 光谱学与光谱分析, 2019, 39(1):223-229.
[27]	吴永清, 李明, 张波, 等. 高光谱成像技术在谷物品质检测中的应用进展[J]. 中国粮油学报, 2021, 36(5):165-173.
[28]	李伟, 赵雪晴, 刘强. 基于高光谱图像光谱变量和颜色特征的霉变玉米籽粒识别[J]. 食品与机械, 2022, 38(12):112-120.
[29]	孙慧婷, 方晓, 徐辉. 基于图像形状特征和纹理的中药材牡丹皮规格分类研究[J]. 黑龙江工程学院学报, 2019, 33(4):40-45.
[30]	刘煊. 不同噪声条件下的高光谱图像特征提取与分类的研究与应用[D]. 开封: 河南大学, 2022.
[31]	孙红敏, 董元, 李晓明, 等. 基于高光谱的小米产地溯源策略与模型研究[J]. 东北农业大学学报, 2021, 52(7):79-88.
[32]	王靖会, 程娇娇, 刘洋, 等. 基于高光谱成像技术鉴别大米品种[J]. 中国农业科技导报, 2021, 23(9):121-128.
[33]	白宗秀, 朱荣光, 王世昌, 等. 高光谱图像结合特征变量筛选定量检测羊肉中狐狸肉掺假[J]. 农业工程学报, 2021, 37(17):276-284.
[34]	刘燕德, 李茂鹏, 胡军, 等. 近红外高光谱的脐橙粒化检测研究[J]. 光谱学与光谱分析, 2022, 42(5):1366-1371.
[35]	ZHAO J L, FANG Y, CHU G M, et al. Identification of leaf-scale wheat powdery mildew (Blumeria graminis f. sp. tritici) combining hyperspectral imaging and an SVM classifier[J]. Plants, 2020, 9(8):936. doi: 10.3390/plants9080936
[36]	GARRIGA M, ROMERO-BRAVO S, ESTRADA F, et al. Estimating carbon isotope discrimination and grain yield of bread wheat grown under water-limited and full irrigation conditions by hyperspectral canopy reflectance and multilinear regression analysis[J]. International Journal of Remote Sensing, 2021, 42(8):2848-2871. doi: 10.1080/01431161.2020.1854888
[37]	刘金秀, 贺小伟, 罗华平, 等. 基于高光谱成像技术的小白杏成熟度判别模型[J]. 食品研究与开发, 2022, 43(15):158-165.
[38]	WAKHOLI C, KANDPAL L M, LEE H, et al. Rapid assessment of corn seed viability using short wave infrared line-scan hyperspectral imaging and chemometrics[J]. Sensors and Actuators B:Chemical, 2018, 255:498-507. doi: 10.1016/j.snb.2017.08.036
[39]	王亚丽, 彭彦昆, 赵鑫龙, 等. 玉米种子活力逐粒无损检测与分级装置研究[J]. 农业机械学报, 2020, 51(2):350-356.
[40]	FENG L, ZHU S S, ZHANG C, et al. Identification of maize kernel vigor under different accelerated aging times using hyperspectral imaging[J]. Molecules, 2018, 23(12):3078. doi: 10.3390/molecules23123078
[41]	ZHANG L, ZHANG Q, WU J, et al. Moisture detection of single corn seed based on hyperspectral imaging and deep learning[J]. Infrared Physics and Technology, 2022, 125:104279. doi: 10.1016/j.infrared.2022.104279
[42]	WANG C P, HUANG W Q, FAN S X, et al. Moisture content detection of maize kernels based on hyperspectral imaging technology and CARS[J]. Laser and Optoelectronics Progress, 2016, 53(12):123001. doi: 10.3788/LOP
[43]	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.
[44]	KIMULI D, WANG W, WANG W, et al. Application of SWIR hyperspectral imaging and chemometrics for identification of aflatoxin B₁ contaminated maize kernels[J]. Infrared Physics and Technology, 2018, 89:351-362. doi: 10.1016/j.infrared.2018.01.026
[45]	YANG D, YUAN J H, CHANG Q, et al. Early determination of mildew status in storage maize kernels using hyperspectral imaging combined with the stacked sparse auto-encoder algorithm[J]. Infrared Physics and Technology, 2020, 109:103412. doi: 10.1016/j.infrared.2020.103412
[46]	SHEN F, HUANG Y, JIANG X S, et al. On-line prediction of hazardous fungal contamination in stored maize by integrating Vis/NIR spectroscopy and computer vision[J]. Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy, 2020, 229:118012. doi: 10.1016/j.saa.2019.118012
[47]	DA CONCEICÃO R R P, SIMEONE M L F, QUEIROZ V A V, et al. Application of near-infrared hyperspectral (NIR) images combined with multivariate image analysis in the differentiation of two mycotoxicogenic Fusarium species associated with maize[J]. Food Chemistry, 2021, 344:128615. doi: 10.1016/j.foodchem.2020.128615
[48]	康孝存, 沈广辉, 徐剑宏, 等. 玉米中伏马毒素B污染高光谱快速检测模型研究[J]. 中国粮油学报, 2023, 38(8):41-48.
[49]	ZHANG J, DAI L M, CHENG F. Classification of frozen corn seeds using hyperspectral VIS/NIR reflectance imaging[J]. Molecules, 2019, 24(1):149. doi: 10.3390/molecules24010149
[50]	WANG Y L, PENG Y K, ZHUANG Q B, et al. Feasibility analysis of NIR for detecting sweet corn seeds vigor[J]. Journal of Cereal Science, 2020, 93:102977. doi: 10.1016/j.jcs.2020.102977
[51]	ZHOU Q, HUANG W, TIAN X, et al. Identification of the variety of maize seeds based on hyperspectral images coupled with convolutional neural networks and subregional voting[J]. Journal of the Science of Food and Agriculture, 2021, 101(11):4532-4542. doi: 10.1002/jsfa.11095 pmid: 33452811
[52]	王庆国, 黄敏, 朱启兵, 等. 基于高光谱图像的玉米种子产地与年份鉴别[J]. 食品与生物技术学报, 2014, 33(2):163-170.