[1]宋镇,姬长英,张波.基于高光谱技术融合图像信息的杏鲍菇干燥过程中含水率检测[J].江苏农业学报,2019,(02):436-444.[doi:doi:10.3969/j.issn.1000-4440.2019.02.026]
　SONG Zhen,JI Chang-ying,ZHANG Bo.Visualized determination of moisture content in Pleurotus eryngii during drying process based on hyperspectral imaging technology[J].,2019,(02):436-444.[doi:doi:10.3969/j.issn.1000-4440.2019.02.026]
点击复制

基于高光谱技术融合图像信息的杏鲍菇干燥过程中含水率检测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年02期
页码:
436-444
栏目:
加工贮藏·质量安全
出版日期:
2019-04-30

文章信息/Info

Title:
Visualized determination of moisture content in Pleurotus eryngii during drying process based on hyperspectral imaging technology
作者:
宋镇; 姬长英; 张波
（南京农业大学工学院，江苏南京210031）
Author(s):
SONG Zhen; JI Chang-ying; ZHANG Bo
(College of Engineering, Nanjing Agricultural University, Nanjing 210031, China)
关键词:
杏鲍菇; 含水率; 高光谱成像; 稳定性竞争自适应重加权采样法; 可视化
Keywords:
Pleurotus eryngii; moisture content; hyperspectral imaging technology; stability competitive adaptive reweighted sampling (SCARS); visualization
分类号:
TS255.3
DOI:
doi:10.3969/j.issn.1000-4440.2019.02.026
文献标志码:
A
摘要:
为了应用高光谱成像技术结合图像处理技术研究杏鲍菇含水率的快速无损检测以及含水率分布可视化，采集不同干燥时期共240个杏鲍菇样品在358～1 021 nm波段范围内的高光谱图像。利用阈值分割方法将图像中杏鲍菇区域与背景分离，提取杏鲍菇的平均光谱数据。采用连续投影算法（SPA）和稳定性竞争自适应重加权采样法（SCARS）分别筛选出5个和10个特征波长；采用主成分分析方法获得杏鲍菇的前2个主成分图像PC1、PC2，基于灰度共生矩阵（GLCM）提取主成分图像PC1、PC2共16个纹理特征。利用偏最小二乘（PLS）和最小二乘支持向量机（LS-SVM）分别建立光谱特征、纹理特征以及光谱与纹理特征融合的含水率预测模型。结果表明：与光谱特征相比，纹理特征与含水率的相关性较差；光谱特征模型SCARS-LS-SVM预测效果最好，其预测集决定系数（R2p）=0.975，均方根误差（RMSEP）=3.712，相对分析误差（RPD）=3.211。基于SCARS-LS-SVM模型，将杏鲍菇样品含水率分布用不同颜色直观显示，实现了含水率分布可视化。
Abstract:
The hyperspectral imaging technology combined with image processing technology was applied to achieve rapid and nondestructive detection of moisture content of Pleurotus eryngii and visualization of moisture content distribution. The hyperspectral images of 240 Pleurotus eryngii samples in different drying periods were obtained in the range of 358-1 021 nm. The threshold segmentation method was used to separate Pleurotus eryngii sample regions from the background regions in the images, and extract the mean spectral data of Pleurotus eryngii. Five and ten characteristic wavelengths were selected by successive projection algorithm (SPA) and stability competitive adaptive reweighted sampling (SCARS), respectively. Principal component analysis method was used to obtain the first two principal component images PC1 and PC2 of Pleurotus eryngii. Sixteen texture features of principal component images PC1 and PC2 were extracted based on gray-level co-occurrence matrix（GLCM）. Finally, moisture content prediction models for spectral features, texture features and fusion features were established by using partial least squares (PLS) and least squares support vector machines (LS-SVM). Results showed that texture features were less correlated with moisture content than spectral features, the spectral feature model SCARS-LS-SVM had the best prediction effect, and the determination coefficient of prediction set (Rp2) was 0.975, root mean square error of prediction set (RMSEP) was 3.712, residual prediction deviation (RPD) was 3.211. Therefore, based on the SCARS-LS-SVM model, the moisture content distribution of Pleurotus eryngii samples was visually displayed in different colors, and the moisture content distribution was visualized.

参考文献/References:

[1]柯乐芹,张东旭,肖建中.杏鲍菇深加工残渣多糖酶法微波辅助提取工艺优化[J].农业工程学报,2014,30(21):332-338.
[2]HU Q，ZHANG M，MUJUMDAR A S, et al. Performance evaluation of vacuum microwave drying of edamame in deep-bed drying[J].Drying Technology，2007，25( 4) : 731-736.
[3]LORENTE D, ALEIXOS N, GMEZ-SANCHIS J, et al. Recent advances and applications of hyperspectral imaging for fruit and vegetable quality assessment[J]. Food and Bioprocess Technology, 2012, 5(4): 1121-1142.
[4]YU K Q, ZHAO Y R, LIU Z Y, et al. Application of visible and nearinfrared hyperspectral imaging for detection of defective features in loquat[J]. Food and Bioprocess Technology, 2014, 7(11): 3077-3087.
[5]XING J，BAERDEMAEKER J．Bruise detection on ‘Jonagold’apples using hyperspectral imagin［J］．Postharvest Biology and Technology，2005，37(2):152-162.
[6]周竹,李小昱,陶海龙,等.基于高光谱成像技术的马铃薯外部缺陷检测[J].农业工程学报,2012,28(21):221-228.
[7]ARIANA D P，LU R F．Evaluation of internal defect and surface color of whole pickles using hyperspectral imaging［J］．Journal of Food Engineering，2010，96(4):583-590.
[8]章海亮,高俊峰,何勇.基于高光谱成像技术的柑橘缺陷无损检测[J].农业机械学报,2013,44(9):177-181.
[9]洪添胜,乔军,NING WANG,等.基于高光谱图像技术的雪花梨品质无损检测[J].农业工程学报，2007，23(2):151-155.
[10]LU R F, PENG Y K. Hyperspectral scattering for assessing peach fruit firmness[J]. Journal of Biosystems Engineering, 2006, 93(2):167-171.
[11]何嘉琳,乔春燕,李冬冬,等.可见-近红外高光谱成像技术对灵武长枣VC含量的无损检测方法[J].食品科学,2018,39(6):194-199.
[12]ELMASRY G, WANG N, ELSAYED A, et al. Hyperspectral imaging for nondestructive determination of some quality attributes for strawberry[J]. Journal of Food Engineering, 2007, 81(1):98-107.
[13]PENG Y K, LU R F. Analysis of spatially resolved hyperspectral scattering images for assessing apple fruit firmness and soluble solids content[J]. Postharvest Biology and Technology, 2008, 48(1): 52-62.
[14]李丹,何建国,刘贵珊,等. 基于高光谱成像技术的小黄瓜水分无损检测[J]. 红外与激光工程, 2014, 43(7): 2393-2397.
[15]王超鹏,黄文倩,樊书祥,等.基于高光谱成像技术与CARS算法的玉米种子含水率检测[J].激光与光电子学进展,2016,53(12):260-267.
[16]赵伟彦,黄敏,朱启兵.基于多模型融合的干燥过程中毛豆含水率、颜色高光谱图像无损检测[J].食品工业科技,2015,36(5):267-271,276.
[17]国家卫生和计划生育委员会.食品中水分的测定: GB5009.3-2016[S]. 北京:中国标准出版社,2016.
[18]何勇,彭继宇,刘飞,等.基于光谱和成像技术的作物养分生理信息快速检测研究进展[J].农业工程学报,2015,31(3):174-189.
[19]雷雨,韩德俊,曾庆东,等.基于高光谱成像技术的小麦条锈病病害程度分级方法[J].农业机械学报,2018,49(5):226-232.
[20]尼珍,胡昌勤,冯芳.近红外光谱分析中光谱预处理方法的作用及其发展[J].药物分析杂志,2008,28(5):824-829.
[21]王欣.近红外分析中光谱预处理方法的研究与应用进展[J].科技资讯,2013(15):2.
[22]潘国锋. 基于K-S算法的水质硝酸盐含量光谱检测方法研究[J]. 光谱实验室, 2011, 28(5): 2700-2704.
[23]于慧春,娄楠,殷勇,等.基于高光谱技术及SPXY和SPA的玉米毒素检测模型建立[J].食品科学,2018,39(16):328-335.
[24]刘国海,夏荣盛,江辉,等.一种基于SCARS策略的近红外特征波长选择方法及其应用[J].光谱学与光谱分析,2014,34(8):2094-2097.
[25]KAMRUZZAMAN M, SUN D W, EIMASRY G, et al. Fast detection and visualization of minced lamb meat adulteration using NIR hyperspectral imaging and multivariate image analysis[J]. Talanta, 2013,103: 130-136.
[26]孙俊,金夏明,毛罕平,等.基于高光谱图像光谱与纹理信息的生菜氮素含量检测[J].农业工程学报,2014,30(10):167-173.

相似文献/References:

[1]胡花丽,张雷刚,李鹏霞.高浓度CO2对采后杏鲍菇乙醛和乙醇含量及其相关酶活性的影响[J].江苏农业学报,2017,(02):432.[doi:doi:10.3969/j.issn.1000-4440.2017.02.030]
　HU Hua-li,ZHANG Lei-gang,LI Peng-xia.Effects of elevated CO2 on aldehyde and ethanol contents and the activities of related enzymes in postharvest Pleurotus eryngii[J].,2017,(02):432.[doi:doi:10.3969/j.issn.1000-4440.2017.02.030]
[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,(02):1051.[doi:doi:10.3969/j.issn.1000-4440.2017.05.014]
[3]韩刚,李瑞平,王思楠,等.基于多尺度遥感数据的荒漠化草原旱情监测及时空特征[J].江苏农业学报,2017,(06):1301.[doi:doi:10.3969/j.issn.1000-4440.2017.06.015]
　HAN Gang,LI Rui-ping,WANG Si-nan,et al.Study on drought monitoring and spatial and temporal characteristics of desertification grassland based on multi-scale remote sensing data[J].,2017,(02):1301.[doi:doi:10.3969/j.issn.1000-4440.2017.06.015]
[4]王海鸥,扶庆权,陈守江,等.不同真空冷冻干燥方法对杏鲍菇片干燥特性及品质的影响[J].江苏农业学报,2018,(04):904.[doi:doi:10.3969/j.issn.1000-4440.2018.04.027]
　WANG Hai-ou,FU Qing-quan,CHEN Shou-jiang,et al.Effect of different vacuum-freezing drying methods on the drying characteristics and qualities of Pleurotus eryngii slices[J].,2018,(02):904.[doi:doi:10.3969/j.issn.1000-4440.2018.04.027]
[5]蔡高委,丛锦玲,齐贝贝.花生种子三轴方向起始破碎力[J].江苏农业学报,2019,(03):716.[doi:doi:10.3969/j.issn.1000-4440.2019.03.030]
　CAI Gao-wei,CONG Jin-ling,QI Bei-bei.Experimental study on initial crushing force of peanut seeds in triaxial direction[J].,2019,(02):716.[doi:doi:10.3969/j.issn.1000-4440.2019.03.030]
[6]尚赏,郭书亚,张艳,等.不同收获期对豫东地区夏玉米机械粒收质量的影响[J].江苏农业学报,2021,(04):867.[doi:doi:10.3969/j.issn.1000-4440.2021.04.008]
　SHANG Shang,GUO Shu-ya,ZHANG Yan,et al.Effects of different harvesting date on mechanical grain-harvesting quality of summer maize in Eastern Henan[J].,2021,(02):867.[doi:doi:10.3969/j.issn.1000-4440.2021.04.008]

备注/Memo

备注/Memo:
收稿日期：2018-07-16 基金项目：江苏省重点研发计划项目（SBE2015310266）；江苏省自然科学基金项目(BK20140729) 作者简介：宋镇（1994-），男，山东淄博人，硕士研究生，研究方向为农产品加工与检测，(E-mail)15852901048@163.com 通讯作者：姬长英，(E-mail)chyji@njau.edu.cn
更新日期/Last Update: 2019-05-05