Rapid Prediction for the Firmness of Guichang Kiwifruit by Hyperspectral Imaging
-
摘要: 为了提高猕猴桃硬度预测的效率。应用可见/近红外（390~1030 nm）高光谱成像系统获取贵长猕猴桃的高光谱图像信息，并提取每个样品感兴趣区域的反射光谱，采用标准正态变换消除原始反射光谱中的噪声干扰；基于竞争性自适应重加权（competitive adaptive reweighted sampling，CARS）与连续投影算法筛选特征变量，建立误差反向传播神经网络和多元线性回归（multi linear regression，MLR）模型检测贵长猕猴桃硬度。结果表明：应用CARS从256个变量中筛选了35个特征变量，运算效率提升了近11倍（即运算时间从5.84 s降到了0.54 s）；构建的CARS-MLR检测模型具有较大的rc=0.95和rp=0.92，较小的RMSEC=1.65 kg/cm2和RMSEP=1.99 kg/cm2，且RPD值（2.47）大于2，表明CARS-MLR模型具有非常好的检测性能，利用高光谱成像技术以及化学计量学可以实现贵长猕猴桃硬度的快速无损检测。Abstract: The work aimed to improve the prediction efficiency in rapid determination of the firmness of kiwifruit. A Vis/NIR (390~1030 nm) hyperspectral imaging system was applied to obtain the images of Guichang kiwifruit, and the reflective spectrum in the regions of interest on each sample was acquired. Noise from original reflective spectrum was reduced by the standard normal variation method. The competitive adaptive reweighted sampling (CARS) and the successive projection algorithm were applied to select feature variables. Finally an error back propagation neural network and a multi linear regression (MLR) model were constructed to predict the firmness of kiwifruit. A total of 35 feature variables were selected by CARS from 256 variables. The working efficiency of the final prediction model was improved by 11-fold, with the runtime dropped from 5.84 s to 0.54 s. Overall, the CARS-MLR model showed a relatively good detection capability (rc=0.95, rp=0.92, RMSEC=1.65 kg/cm2, RMSEP=1.99 kg/cm2, RPD above 2). This study demonstrated the application potential of the nondestructive hyperspectral imaging technology for fast determination of the firmness of kiwifruit.
-
Key words:
- Guichang kiwifruit /
- firmness /
- hyperspectral imaging /
- chemometrics /
- nondestructive detection
-
图 4 SPA筛选特征变量结果
Figure 4. Results of feature variables selected by SPA
注：a.均方根误差随着变量数的改变规律；b.SPA筛选的特征变量。
图 5 CARS筛选特征变量的结果
Figure 5. Results of feature variables selected by CARS
注：a.交叉验证均方根误差随着采样次数的改变规律；b.采样变量数随着采样次数的改变规律；c.CARS筛选的特征变量。
图 6 猕猴桃硬度参考值与预测值
Figure 6. Reference and predicted values of the firmness of kiwifruit
表 1 猕猴桃硬度值
Table 1. Values of kiwifruit firmness
样本集 样本数 硬度（kg/cm2） 最小值 最大值 平均值 标准差 建模集 120 1.99 18.80 10.54 5.31 预测集 40 2.02 18.76 13.27 4.92 
下载: 导出CSV
表 2 猕猴桃硬度BP和MLR检测模型
Table 2. BP and MLR detection models for the firmness of kiwifruit
模型 特征变量
筛选方法变量数 建模集 预测集 rc RMSEC
（kg/cm2）rp RMSEP
（kg/cm2）RPD BP SPA 22 0.80 3.19 0.79 2.97 1.66 CARS 35 0.93 2.11 0.87 2.43 2.02 MLR SPA 22 0.81 3.08 0.80 2.95 1.67 CARS 35 0.95 1.65 0.92 1.99 2.47 
下载: 导出CSV
-
[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 J H, DU C, LIANG C, et al. Extraction and antioxidant activity of polysaccharides from Guichang kiwifruit[J]. Food Science,2016,37(20):19?23. doi: 10.7506/spkx1002-6630-201620004 [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 C, LI M, LONG Y H, 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. doi: 10.7506/spkx1002-6630-201622042 [3] 靳政时, 牛犇, 刘瑞玲, 等. 干燥方式对猕猴桃果干品质的影响[J]. 食品工业科技,2022,43(24):62?71. [JIN Z S, NIU B, LIU R L, et al. Effects of drying methods on the quality of dried kiwifruit[J]. Science and Technology of Food Industry,2022,43(24):62?71. [4] 曹念念, 刘强, 彭菁, 等. 基于近红外光谱技术的黄桃脆片可溶性固形物和硬度定量检测方法[J]. 食品机械,2021,37(3):51?57. [CAO N N, LIU Q, PENG J, et al. Study on quantitative detection of soluble solids and firmness of yellow peach chips by near-infrared spectroscopy[J]. Food Machinery,2021,37(3):51?57. [5] 胡逸磊, 姜洪喆, 周宏平, 等. 水果成熟度近红外光谱及高光谱成像无损检测研究进展[J]. 食品工业科技,2021,42(20):377?383. [HU Y L, JIANG H Z, ZHOU H P, et al. Research progress on nondestructive detection of fruit maturity by near infrared spectroscopy and hyperspectral imaging[J]. Science and Technology of Food Industry,2021,42(20):377?383. doi: 10.13386/j.issn1002-0306.2020070074 [6] DEVASSY B M, GEORGE S. Estimation of strawberry firmness using hyperspectral imaging: A comparison of regression models[J]. Journal of Spectral Imaging,2021,10(a3):1?14. [7] 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 L J, CHEN M, WANG Y C, 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. [8] HU W H, SUN D W, 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. doi: 10.1016/j.postharvbio.2016.11.001 [9] ZHANG H L, ZHAN B S, PAN F, 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(111148):1?9. [10] LI X L, WEI Y Z, XU J, 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. doi: 10.1016/j.postharvbio.2018.05.003 [11] PULLANAGARI R R, LI M. Uncertainty assessment for firmness and total soluble solids of sweet cherries using hyperspectral imaging and multivariate statistics[J]. Journal of Food Engineering,2020,289(110177):1?12. [12] 蔡正云, 吴龙国, 王菁, 等. 宁夏赤霞珠葡萄水分含量的高光谱无损检测研究[J]. 食品工业科技,2017,38(2):79?88. [CAI Z Y, WU L G, WANG J, et al. Non-destructive determination of moisture composition in Ningxia wine grapes based on visible near-infrared hyperspectral imaging technique[J]. Science and Technology of Food Industry,2017,38(2):79?88. doi: 10.13386/j.issn1002-0306.2017.02.007 [13] LEIVA-VALENZUELA G A, LU R, AGUILERA J M. Assessment of internal quality of blueberries using hyperspectral transmittance and reflectance images with whole spectra or selected wavelengths[J]. Innovative Food Science & Emerging Technologies,2014,24:2?13. [14] 高升, 王巧华, 施行, 等. 便携式红提葡萄多品质可见/近红外检测仪设计与试验[J]. 农业机械学报,2021,52(2):308?319. [GAO S, WANG Q H, SHI X, et al. Design and test of portable red globe grape extraction multi-quality visible/near infrared detector[J]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(2):308?319. doi: 10.6041/j.issn.1000-1298.2021.02.030 [15] 刘卉, 郭文川, 岳绒. 猕猴桃硬度近红外漫反射光谱无损检测[J]. 农业机械学报,2011,42(3):145?149. [LIU H, GUO W C, YUE R. Non-destructive detection of kiwifruit firmness based on near-infrared diffused spectroscopy[J]. Transactions of the Chinese Society for Agricultural Machinery,2011,42(3):145?149. [16] 马佳佳, 王克强. 水果品质光学无损检测技术研究进展[J]. 食品工业科技,2021,42(23):427?437. [MA J J, WANG K Q. Research progress of optical nondestructive testing technology for fruit quality[J]. Science and Technology of Food Industry,2021,42(23):427?437. [17] XIE C Q, CHU B Q, HE Y. Prediction of banana color and firmness using a novel wavelengths selection method of hyperspectral imaging[J]. Food Chemistry,2018,245:132?140. doi: 10.1016/j.foodchem.2017.10.079 [18] LI B, 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. doi: 10.1016/j.postharvbio.2018.03.008 [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 Y Y, WANG Y X, XUAN G T, 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. doi: 10.6041/j.issn.1000-1298.2020.08.038 [20] MENG Q L, SHANG J, HUANG R S, et al. Determination of soluble solids content and firmness in plum using hyperspectral imaging and chemometric algorithms[J]. Journal of Food Process Engineering,2021,44(1):1?9. [21] 孟庆龙, 尚静, 黄人帅, 等. 基于主成分回归的猕猴桃可溶性固形物无损检测[J]. 包装工程,2021,42(3):19?24. [MENG Q L, SHANG J, HUANG R S, et al. Nondestructive detection for soluble solids content of kiwifruits based on principal component regression[J]. Packaging Engineering,2021,42(3):19?24. [22] 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: 67?68.NI L J, ZHANG L G. Basic chemometrics and its application[M]. Shanghai: East China University of Science and Technology Press, 2011: 67?68. [23] 郭文川, 董金磊. 高光谱成像结合人工神经网络无损检测桃的硬度[J]. 光学精密工程,2015,23(6):1530?1537. [GUO W C, DONG J L. Nondestructive detection on firmness of peaches based on hyperspectral imaging and artificial neural networks[J]. Optics and Precision Engineering,2015,23(6):1530?1537. doi: 10.3788/OPE.20152306.1530 [24] NICOLA? B, BEULLENS K, BOBELYN E, et al. Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review[J]. Postharvest Biology and Technology,2007:99?118. [25] 于雷, 章涛, 朱亚星, 等. 基于IRIV算法优选大豆叶片高光谱特征波长变量估测SPAD值[J]. 农业工程学报,2018,34(16):148?154. [YU L, ZHANG T, ZHU Y X, et al. Determination of soybean leaf SPAD value using characteristic wavelength variables preferably selected by IRIV algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering,2018,34(16):148?154. doi: 10.11975/j.issn.1002-6819.2018.16.019 [26] GALV?O R K H, ARAUJO M C U, JOSé G E, et al. A method for calibration and validation subset partitioning[J]. Talanta,2005,67(4):736?740. doi: 10.1016/j.talanta.2005.03.025 -
下载:
下载:
下载:
下载:
下载:
下载:
点击查看大图
图(6) / 表(2)
计量
- 文章访问数: 38
- HTML全文浏览量: 15
- PDF下载量: 10
- 被引次数: 0
下载:
