高光谱成像结合模式识别无损检测猕猴桃成熟度

doi:10.13733/j.jcam.issn.20955553.2022.08.013

摘要/Abstract

摘要： 为实现“贵长”猕猴桃成熟度的快速无损检测，提出高光谱成像结合模式识别建立识别模型的检测方法。首先利用可见/近红外(390~1 030 nm)高光谱成像系统采集不同成熟阶段猕猴桃样本的高光谱图像，并获取整个样本区域的光谱反射率。然后对比3种光谱预处理方法：二阶导数、标准正态变换以及多元散射校正对原始光谱的预处理效果。最后分析偏最小二乘判别分析(PLS-DA)和简化的K最近邻(SKNN)模式识别方法对猕猴桃成熟度的识别性能。结果表明：相对于标准正态变换和多元散射校正两种光谱预处理方法，二阶导数预处理方法对原始光谱的预处理效果相对较好。另外，PLS-DA识别模型对猕猴桃成熟度的识别性能要优于SKNN识别模型，其正确识别率达到100%。表明采用高光谱成像技术结合模式识别方法判别“贵长”猕猴桃成熟度是可行的。

关键词: “贵长”猕猴桃, 成熟度, 高光谱成像, 模式识别, 无损检测

Abstract: In order to detect the maturity of ‘Guichang’ kiwifruit quickly and nondestructively, a detection method based on hyperspectral imaging and pattern recognition was proposed. Firstly, the Vis/NIR hyperspectral imaging system (390-1 030 nm) was used to collect hyperspectral images of kiwifruit samples at different maturity stages and the spectra reflectance in the regions of whole samples was extracted. Secondly, the preprocessing effectiveness of second derivative (SD), standard normal variation (SNV) and multiscatter calibration (MSC) on the original spectra was compared and evaluated. Finally, partial least square discrimination (PLS-DA) analysis and simplified K nearest neighbor (SKNN) recognition models were built to distinguish the maturity of kiwifruit. The experimental results showed that the preprocessing effectiveness of second derivative was better than standard normal variation and multiscatter calibration. The correct identification rates of PLS-DA recognition model reached 100%, exhibiting a relatively better recognition ability than SKNN recognition model. Therefore, it is possible to determine the maturity of ‘Guichang’ kiwifruits by hyperspectral imaging technology and pattern recognition.

Key words: ‘Guichang’ kiwifruits, maturity, hyperspectral imaging, pattern recognition, nondestructive detection

中图分类号:

O657.3： S663.4

尚静, 黄人帅, 张艳, 张书琴, 孟庆龙, . 高光谱成像结合模式识别无损检测猕猴桃成熟度[J]. 中国农机化学报, 2022, 43(8): 90-95.

Shang Jing, Huang Renshuai, Zhang Yan, Zhang Shuqin, Meng Qinglong.. Nondestructive detection for maturity of kiwifruit based on hyperspectral imaging and pattern recognition[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(8): 90-95.

参考文献

［1］　
王金华, 杜超, 梁晨, 等. 贵长猕猴桃多糖提取工艺及体外抗氧化功能［J］. 食品科学, 2016, 37(20): 19-23.

Wang Jinhua, Du Chao, Liang Chen, et al. Extraction and antioxidant activity of polysaccharides from Guichang kiwifruit ［J］. Food Science, 2016, 37(20): 19-23.

［2］　
张承, 李明, 龙友华, 等. 采前喷施壳聚糖复合膜对猕猴桃软腐病的防控及其保鲜作用［J］. 食品科学, 2016, 37(22): 274-281.

Zhang Cheng, Li Ming, Long Youhua, et al. Control of soft rot in kiwifruit by preharvest application of chitosan composite coating and its effect on preserving and improving kiwifruit quality ［J］. Food Science, 2016, 37(22): 274-281.

［3］　
王芹志, 强锋, 何建国, 等. 基于可见—近红外光谱预测灵武长枣脆度及模型优化［J］. 食品与发酵工业, 2017, 43(3): 205-211.

Wang Qinzhi, Qiang Feng, He Jianguo, et al. The model of predicting of the brittleness of lingwu jujube by visiblenear infrared spectroscopy and its optimization ［J］. Food and Fermentation Industries, 2017, 43(3): 205-211.

［4］　
霍迎秋, 张晨, 李宇豪, 等. 高光谱图像结合机器学习方法无损检测猕猴桃［J］. 中国农机化学报, 2019, 40(4): 71-77.

Huo Yingqiu, Zhang Chen, Li Yuhao, et al. Nondestructive detection for kiwifruit based on the hyperspectral technology and machine learning ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(4): 71-77.

［5］　
许丽佳, 陈铭, 王玉超, 等. 高光谱成像的猕猴桃糖度无损检测方法［J］. 光谱学与光谱分析, 2021, 41(7): 2188-2195.

Xu Lijia, Chen Ming, Wang Yuchao, et al. Study on nondestructive detection method of kiwifruit sugar content based on hyperspectral imaging technology ［J］. Spectroscopy and Spectral Analysis, 2021, 41(7): 2188-2195.

［6］　
Fan Shuxiang, Zhang Baohua, Li Jiangbao, et al. Prediction of soluble solids content of apple using the combination of spectra and textural featuresof hyperspectral reflectance imaging data ［J］. Postharvest Biology and Technology, 2016, 121: 51-61.

［7］　
Li Xiaoli, Wei Yuzhen, Xu Jie, et al. SSC and pH for sweet assessment and maturity classification of harvested cherry fruit based on NIR hyperspectral imaging technology ［J］. Postharvest Biology and Technology, 2018, 143: 112-118.

［8］　
Zhang Hailiang, Zhan Baishao, Pan Fan, et al. Determination of soluble solids content in oranges using visible and near infrared full transmittance hyperspectral imaging with comparative analysis of models ［J］. Postharvest Biology and Technology, 2020, 163: 1-9.

［9］　
Huang Min, Lu Renfu. Apple mealiness detection using hyperspectral scattering technique ［J］. Postharvest Biology and Technology, 2010, 58(3): 168-175.

［10］　
Fan Shuxiang, Li Jiangbao, Xia Yu, et al. Longterm evaluation of soluble solids content of apples with biological variability by using nearinfrared spectroscopy and calibration transfer method ［J］. Postharvest Biology and Technology, 2019, 151: 79-87.

［11］　
Xie Chuanqi, Chu Bingquan, He Yong. Prediction of banana color and firmness using a novel wavelengths selection method of hyperspectral imaging ［J］. Food Chemistry, 2018, 245: 132-140.

［12］　
董金磊, 郭文川. 采后猕猴桃可溶性固形物含量的高光谱无损检测［J］. 食品科学, 2015, 36(16): 101-106.

Dong Jinlei, Guo Wenchuan. Nondestructive detection of soluble solid content of postharvest kiwifruits based on hyperspectral imaging technology ［J］. Food Science, 2015, 36(16): 101-106.

［13］　
Hu Weihong, Sun Dawen, Blasco J. Rapid monitoring 1-MCP-induced modulation of sugars accumulation in ripening ‘Hayward’ kiwifruit by Vis/NIR hyperspectral imaging ［J］. Postharvest Biology and Technology, 2017, 125: 168-180.

［14］　
Sun Ye, Gu Xinzhe, Sun Ke, et al. Hyperspectral reflectance imaging combined with chemometrics and successive projections algorithm for chilling injury classification in peaches ［J］. LWT, 2017, 75: 557-564.

［15］　
Li Bo, CoboMedina M, Lecourt J, et al. Application of hyperspectral imaging for nondestructive measurement of plum quality attributes ［J］. Postharvest Biology and Technology, 2018, 141: 8-15.

［16］　
詹白勺, 倪君辉, 李军. 高光谱技术结合CARS算法的库尔勒香梨可溶性固形物定量测定［J］. 光谱学与光谱分析, 2014, 34(10): 2752-2757.

Zhan Baishao, Ni Junhui, Li Jun. Hyperspectral technology combined with CARS algorithm to quantitatively determine the SSC in korla fragrant pear ［J］. Spectroscopy and Spectral Analysis, 2014, 34(10): 2752-2757.

［17］　
Yu Xinjie, Lu Huanda, Wu Di. Development of deep learning method for predicting firmness and soluble solid content of postharvest korla fragrant pear using VIS/NIR hyperspectral reflectance imaging ［J］. Postharvest Biology and Technology, 2018, 141: 39-49.

［18］　
Zhang Chu, Guo Chentong, Liu Fei, et al. Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine ［J］. Journal of Food Engineering, 2016, 179: 11-18.

［19］　
邵园园, 王永贤, 玄冠涛, 等. 基于高光谱成像的肥城桃品质可视化分析与成熟度检测［J］. 农业机械学报, 2020, 51(8): 344-350.

Shao Yuanyuan, Wang Yongxian, Xuan Guantao, et al. Visual detection of SSC and firmness and maturity prediction for Feicheng peach by using hyperspectral imaging ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(8): 344-350.

［20］　
Kennard R W, Stone L A. Computer aided design of experiments ［J］. Technometrics, 1969, 11(1): 137-148.

［21］　
倪力军, 张立国. 基础化学计量学及其应用［M］. 上海: 华东理工大学出版社, 2011.

[1]	王菁, 范晓飞, 赵智慧, 张君, 孙磊, 索雪松. 基于YOLO算法的不同品种枣自然环境下成熟度识别[J]. 中国农机化学报, 2022, 43(11): 165-171.
[2]	翁海勇;许金钗;陶铸;刘江洪;郑金贵;叶大鹏;. 高EGCG含量茶树品种光谱识别模型构建[J]. 中国农机化学报, 2021, 42(6): 111-117.
[3]	蔡泽宇;刘政;张光跃;杨腾祥;金诚谦;. 谷物含水率测量技术研究进展[J]. 中国农机化学报, 2021, 42(4): 99-109.
[4]	张伏;张朝臣;陈自均;滕帅;徐锐良;. 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.
[5]	张娟利;宋朝阳;韩文霆;尚晓明;刘治开;. 基于RGB图像处理的烟叶水分无损检测方法研究[J]. 中国农机化学报, 2019, 40(5): 62-68.
[6]	袁明新;于洪涛;江亚峰;王琪;申燚;. 联合迁移学习和自适应学习率的苹果成熟度识别[J]. 中国农机化学报, 2019, 40(11): 131-135.