Abstract
Objective: To identify mildew maize kernels accurately. Methods: A novel method to identify mildew maize kernels using spectral variables and color characteristics of hyperspectral images. Firstly, image segmentation, spectral variables and color features extraction were carried out on maize kernel images. Then, color features of maize kernel images were utilized to generate color histograms. Additionally, spectral variables and color histogram features were combined into a feature set. Finally, the distance functions were used to analyze the features in this feature set to identify mildew maize kernels. Results: For the proposed method, the maximum average identification deviation and accuracy for the mildew maize kernels were 1.12 and 97.59%, respectively. Compared with the method based on hyperspectral images+random frog+extreme learning machine, the method using hyperspectral images+colony optimization + BP neural network, and the method based on hyperspectral images+sparse auto-encoders + convolutional neural network, the identification accuracies of mildew maize kernels were significantly improved by the proposed method. Conclusion: The developed method can accurately identify whether the corn grain samples are mildew and the mildew degree of the maize kernel samples.
Publication Date
12-28-2022
First Page
112
Last Page
120
DOI
10.13652/j.spjx.1003.5788.2022.60097
Recommended Citation
Wei, LI; Xue-qing, ZHAO; and Qiang, LIU
(2022)
"Research on the identification of mildew maize kernels using spectral variables and color features of hyperspectral images,"
Food and Machinery: Vol. 38:
Iss.
12, Article 19.
DOI: 10.13652/j.spjx.1003.5788.2022.60097
Available at:
https://www.ifoodmm.cn/journal/vol38/iss12/19
References
[1] 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):5 333.
[2] REN X,TIAN H,ZHAO K,et al.Research on pH value detection method during maize silage secondary fermentation based on computer vision[J].Agriculture,2022,12(10):1 623.
[3] 罗财伟,王茂飞,宁冬,等.不同类型和含水量玉米储存期间理化性质及糊化特性变化研究-[J/OL-].中国畜牧杂志.(2022-10-10)-[2022-11-05-].https://doi.org/10.19556/j.0258-7033.20220114-08.LUO C W,WANG M F,NING D,et al.Study on changes of physicochemical properties and gelatinization characteristics of maize with different types and water content during storage-[J/OL-].Chinese Journal of Animal Science.(2022-10-10)-[2022-11-05-].https://doi.org/10.19556/j.0258-7033.20220114-08.
[4] GUO Z M,WANG M M,WU J Z,et al.Quantitative assessment of zearalenone in maize using multivariate algorithms coupled to Raman spectroscopy[J].Food Chemistry,2019,286:282-288.
[5] 戴松松,殷勇.基于高光谱信息特征选择的玉米霉变程度Fisher鉴别方法[J].食品与机械,2018,34(3):68-72.DAI S S,YIN Y.Fisher discriminant analysis for moldy degrees of maize samples based on the feature selection of hyperspectral data[J].Food & Machinery,2018,34(3):68-72.
[6] 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):4 612-4 651.
[7] ZHANG L,WANG Y,WEI Y,et al.Near-infrared hyperspectral imaging technology combined with deep convolutional generative adversarial network to predict oil content of single maize kernel[J].Food Chemistry,2022,370:131047.
[8] 钱佳成,宋伟.不同储藏条件下玉米挥发性成分研究[J].食品工业科技,2020,41(16):252-258,265.QIAN J C,SONG W.Analysis of volatile components of corn under different storage conditions[J].Science and Technology of Food Industry,2020,41(16):252-258,265.
[9] GU S,CHEN W,WANG Z H,et al.Rapid detection of Aspergillus spp.infection levels on milled rice by headspace-gas chromatography ion-mobility spectrometry(HS-GC-IMS)and E-nose[J].LWT-Food Science and Technology,2020,132:109758.
[10] SHEN F,HUANG Y,JIANG X,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.
[11] 王林柏,刘景艳,周玉宏,等.基于分水岭算法结合卷积神经网络的玉米种子质量检测[J].中国农机化学报,2021,42(12):168-174.WANG L B,LIU J Y,ZHOU Y H,et al.Corn seed quality detection based on watershed algorithm and convolutional neural network[J].Journal of Chinese Agricultural Mechanization,2021,42(12):168-174.
[12] 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 & Technology,2020,109:103412.
[13] 彭彦昆,戴宝琼,李阳,等.玉米主要品质便携式检测装置设计与试验[J].农业机械学报,2022,53(9):382-389.PENG Y K,DAI B Q,LI Y,et al.Design and experiment of portable device for testing main quality in corn[J].Transactions of the Chinese Society for Agricultural Machinery,2022,53(9):382-389.
[14] HU Y T,WANG Z,LI X F,et al.Nondestructive classification of maize moldy seeds by hyperspectral imaging and optimal machine learning algorithms[J].Sensors,2022,22(16):6 064.
[15] 王光辉,殷勇.基于高光谱融合神经网络的玉米黄曲霉毒素B1和赤霉烯酮含量预测[J].食品与机械,2018,34(11):64-69.WANG G H,YIN Y.Detection of moldy maize aflatoxin B1 and gibberellin by hyperspectral coupled with neural network[J].Food & Machinery,2018,34(11):64-69.
[16] ZHOU Q,HUANG W Q,FAN S X,et al.Non-destructive discrimination of the variety of sweet maize seeds based on hyperspectral image coupled with wavelength selection algorithm[J].Infrared Physics & Technology,2020,109:103418.
[17] MA J,PU H B,SUN D W,et al.Application of Vis-NIR hyperspectral imaging in classification between fresh and frozen-thawed pork Longissimus Dorsi muscles[J].International Journal of Refrigeration,2015,50:10-18.
[18] 杨东,王舒卉,吴建华,等.玉米籽粒霉变等级高光谱图像检测方法研究-[J/OL-].中国粮油学报.(2022-05-17)-[2022-11-05-].https://kns.cnki.net/kcms/detail/11.2864.TS.20220516.2032.004.html.YANG D,WANG S H,WU J H,et al.Study on hyperspectral image detection method of maize grain mildew grade[J].Journal of the Chinese Cereals and Oils Association.(2022-05-17)-[2022-11-05-].https://kns.cnki.net/kcms/detail/11.2864.TS.20220516.2032.004.html.
[19] LIU Z W,JIANG J B,QIAO X J,et al.Using convolution neural network and hyperspectral image to identify moldy peanut kernels[J].LWT-Food Science and Technology,2020,132:109815.
[20] WANG W C,HUANG W Q,YU H S,et al.Identification of maize with different moldy levels based on catalase activity and data fusion of hyperspectral images[J].Foods,2022,11(12):1 727.
[21] 中华人民共和国标准化法[S].北京:中国民主法制出版社,2017:1-6.Standardization law of the peoples republic of China[S].Beijing:China Democracy and Legal System Publishing House,2017:1-6.
[22] 国家发展和改革委员会,国家粮食局和物资储备局,财政部,等.关于执行粮油质量国家标准有关问题的规定[J].粮食科技与经济,2022,47(Z1):65-67.National Development and Reform Commission,National Food and Strategic Reserves Administration,Ministry of Finance,et al.Provisions on issues related to the implementation of national standards for grain and oil quality[J].Food Science and Technology and Economy,2022,47(Z1):65-67.
[23] LI J B,HUANG W Q,CHEN L P,et al.Variable selection in visible and near-infrared spectral analysis for noninvasive determination of soluble solids content of 'Ya' pear[J].Food Analytical Methods,2014,7(9):1 891-1 902.
[24] ZHOU J X,LIU X,XU T W,et al.A new fusion approach for content based image retrieval with color histogram and local directional pattern[J].International Journal of Machine Learning and Cybernetics,2018,9(4):677-689.
[25] BHUNIA A K,BHATTACHARYYA A,BANERJEE P,et al.A novel feature descriptor for image retrieval by combining modified color histogram and diagonally symmetric co-occurrence texture pattern[J].Pattern Analysis and Applications,2020,23(2):703-723.
[26] YANG D,JIANG J Y,JIE Y,et al.Detection of the moldy status of the stored maize kernels using hyperspectral imaging and deep learning algorithms[J].International Journal of Food Properties,2022,25(1):170-186.
[27] JIA Y,LI Z,GAO R,et al.Mildew recognition on maize seed by use of hyperspectral technology[J].Spectroscopy Letters,2022,55(4):240-249.