基于高光谱图像信息融合的红提糖度无损检测

高升; 王巧华

doi:10.3788/fgxb20194012.1574

您当前的位置：

首页 >

文章列表页 >

基于高光谱图像信息融合的红提糖度无损检测

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 基于高光谱图像信息融合的红提糖度无损检测
- Comprehensive Detection of Internal Quality of Red Globe Grape Extract Based on Near Infrared Spectroscopy
- 发光学报 2019年40卷第12期页码：1574-1584
- 作者机构：
  
  1. 华中农业大学工学院, 湖北武汉 430070
  2. 农业农村部长江中下游农业装备重点实验室, 湖北武汉 430070
- 作者简介：
- 基金信息：
  
  国家自然科学基金（31871863）();湖北省自然科学基金（2012FKB02910）();湖北省研究与开发计划（2011BHB016）资助项目()
- DOI：10.3788/fgxb20194012.1574
  中图分类号： O657.3;TS255.2
- 收稿日期：2019-06-24，
  
  修回日期：2019-07-28，
  
  网络出版日期：2019-12-05，
  
  纸质出版日期：2019-12-05
- 稿件说明：
移动端阅览
高升, 王巧华,. 基于高光谱图像信息融合的红提糖度无损检测[J]. 发光学报, 2019,40(12): 1574-1584

GAO Sheng, WANG Qiao-hua,. Comprehensive Detection of Internal Quality of Red Globe Grape Extract Based on Near Infrared Spectroscopy[J]. Chinese Journal of Luminescence, 2019,40(12): 1574-1584
高升, 王巧华,. 基于高光谱图像信息融合的红提糖度无损检测[J]. 发光学报, 2019,40(12): 1574-1584 DOI： 10.3788/fgxb20194012.1574.

GAO Sheng, WANG Qiao-hua,. Comprehensive Detection of Internal Quality of Red Globe Grape Extract Based on Near Infrared Spectroscopy[J]. Chinese Journal of Luminescence, 2019,40(12): 1574-1584 DOI： 10.3788/fgxb20194012.1574.

摘要

红提糖度是重要的内部品质衡量指标，传统的检测方法均为破坏性生化检测，本文基于高光谱成像技术，提出了一种基于高光谱信息融合的红提糖度含量无损检测方法。采集并提取260个红提样本的光谱信息和图像信息，对光谱信息分别利用SNV、S-G等光谱预处理方法建立PLSR模型，确定最好的光谱预处理方法，分别采用一次降维（GA、CARS、IRIV）算法和组合降维算法（CARS-SPA、IRIV-SPA、GA-SPA）共六种降维方法对光谱信息进行特征变量提取；获取灰度共生矩阵的图像纹理信息，结合图像的颜色信息（R、G、B、H、S、V、L、a、b），组成19个图像特征参数，采用PCA算法对图像信息进行降维，分别建立基于降维处理后的光谱信息、图像信息以及两者融合的红提糖度线性预测模型PLSR、非线性预测模型LSSVM，并对比分析模型的优劣。结果表明，若只利用光谱信息建模，IRIV-SPA可有效地提取红提糖度光谱信息的特征波长，提高模型的预测性能；若只利用图像信息进行建模，模型的预测性能不好，PCA降维有效地提高了模型的预测性能，但提高的性能有限；将IRIV-SPA特征波段提取后的光谱和经PCA降维后的图像信息进行融合，分别建立PLSR和LSSVM模型，红提糖度的最优PLSR模型的校正集和预测集相关系数分别为0.943，0.941；红提糖度的最优LSSVM模型的校正集和预测集相关系数分别为0.954，0.952。LSSVM所建模型的效果好于PLSR所建模型，但模型的运算时间较长。两种模型的精度均比单方面基于光谱或图像信息的模型都有较大的提高，表明融合高光谱图像的光谱与图像信息不仅可以提高模型的运算速度、简化模型，同时有效地提高了红提糖度预测性能，为红提糖度的检测找到了一种新的方法。

Abstract

The sugar content of red grapes is an important index to measure its internal quality. The conventional methods based on biochemistry to test the sugar content are all destructive. This article proposed a method using high spectrum technology for sugar content test which does not break the fruit at all. The spectral and graphical information is collected and extracted from 260 samples. PLSR model was set up by the usage of preprocessing method like SNV and S-G

which is aiming to find out the fittest one. We adopted six algorithms including GA

CARS and IRIV from one-time dimension-reducting algorithm and CARS-SPA

IRIV-SPA and GA-SPA from combined dimension-reducting algorithm respectively

to extract the characteristic variable from the spectral information. 19 characteristic parameters were obtained from the texture information of images by gray-level co-occurrence matrix and the color information respectively by RGB model. After reducing the dimensions of image information with PCA algorithm

we built the linear predictive model PLSR and non-linear predictive model LSSVM

which were based on the dimension-reduced spectral information

image information and the combination of the formers separately

then compare the efficiency of models. The results show that

when we modeled with spectral information merely

the IRIV-SPA was able to extract the characteristic wavelength of the spectrum information of red grape's sugar content; comparely

the model built with information of images only did not work well

even though the PCA that reduced the dimensions effectively increased the performance of model's prediction but limitedly. We built the PLSR model and LSSVM model with both spectral wave-range characteristics by IRIV-SPA and image information dimension-reduced by PCA. The correlation coefficient of optimal PLSR model's calibration set and prediction set is 0.943 and 0.941 respectively while 0.954 and 0.952 for LSSVM model. The performance of model of LSSVM was better than PLSR

but the former one took more time for operation. The relatively greater promotion on accuracy of both models based on the combination of two classifications of characteristics indicated that the combination of spectral information and image information was not just able to increase the operating speed and simplify the model but effectively promote the performance of the prediction for red grape's sugar content. Thus a new method for the detection of red globe grape sugar content was found.

关键词

Keywords

references

国家统计局. 中国统计年鉴[M]. 北京:中国统计出版社, 2018. National Bureau of Statistics. China Statistical Yearbook[M]. Beijing:China Statistics Press, 2018. (in Chinese)

ZHANG D Y,XU L,WANG Q W,et al.. The optimal local model selection for robust and fast evaluation of soluble solid content in melon with thick peel and large size by Vis-NIR spectroscopy[J]. Food Anal. Methods, 2019,12(1):136-147.

XU X,XU H R,XIE L J,et al.. Effect of measurement position on prediction of apple soluble solids content (SSC) by an on-line near-infrared (NIR) system[J]. J. Food Meas. Charact., 2019,13(1):506-512.

中华人民共和国农业部. NY/T 2637-2014水果和蔬菜可溶性固形物含量的测定折射仪法[S]. 北京:中国农业出版社, 2015. The Ministry of Agriculture of the People's Republic of China. NY/T 2637-2014 Refractometric Method for Determination of Total Soluble Solids in Fruits and Vegetables[S]. Beijing:China Agriculture Press, 2015. (in Chinese)

李雄,刘燕德,欧阳爱国,等. 基于近红外的柚子品种判别和糖度检测通用模型[J]. 发光学报, 2019,40(6):808-814. LI X,LIU Y D,OUYANG A G,et al.. A general model for judging and brix detection of grapefruit variety based on near infrared[J]. Chin. J. Lumin., 2019,40(6):808-814. (in Chinese)

王怡淼,朱金林,张慧,等. 基于MC-UVE、GA算法及因子分析对葡萄酒酒精度近红外定量模型的优化研究[J]. 发光学报, 2018,39(9):1310-1316. WANG Y M,ZHU J L,ZHANG H,et al.. Optimization of near infrared quantitative model for wine alcohol content based on MC-UVE,GA algorithm and factor analysis[J]. Chin. J. Lumin., 2018,39(9):1310-1316. (in Chinese)

秦玉华,张海涛,高锐,等. 基于近红外光谱及主成分雷达图特征提取的产品质量稳定性研究[J]. 发光学报,2018,39(11):1627-1632. QIN Y H,ZHAGN H T,GAO R,et al.. Research on products quality stability based on near infrared spectroscopy and feature extraction of PCA radar chart[J]. Chin. J. Lumin., 2018,39(11):1627-1632. (in Chinese)

饶利波,陈晓燕,庞涛. 基于光谱技术的Bipls算法结合CARS算法的苹果可溶性固形物含量检测[J]. 发光学报, 2019,40(3):389-395. RAO L B,CHEN X Y,PANG T. Determination of apple soluble solids content using Bipls coupled with CARS algorithm based on spectral technology[J]. Chin. J. Lumin., 2019,40(3):389-395. (in Chinese)

介邓飞,李泽海,赵竣威,等. 基于高光谱漫透射成像可视化检测脐橙可溶性固形物[J]. 发光学报, 2017,38(5):685-691. JIE D F,LI Z H,ZHAO J W,et al.. Visualized detection of soluble solid content distribution of navel orange based on hyperspectral diffuse transmittance imaging[J]. Chin. J. Lumin., 2017,38(5):685-691. (in Chinese)

王转卫,迟茜,郭文川,等. 基于近红外光谱技术的发育后期苹果内部品质检测[J]. 农业机械学报, 2018,49(5):348-354. WANG Z W,CHI Q,GUO W C,et al.. Internal quality detection of apples during late developmental period based on near-infrared spectral technology[J]. Trans. Chin. Soc. Agric. Mach., 2018,49(5):348-354. (in Chinese)

彭彦昆,赵芳,白京,等. 基于图谱特征的番茄种子活力检测与分级[J]. 农业机械学报, 2018,49(2):327-333. PENG Y K,ZHAO F,BAI J,et al.. Detection and classification of tomato seed vitality based on image processing[J]. Trans. Chin. Soc. Agric. Mach., 2018,49(2):327-333. (in Chinese)

金瑞,李小昱,颜伊芸,等. 基于高光谱图像和光谱信息融合的马铃薯多指标检测方法[J]. 农业工程学报, 2015,31(16):258-263. JIN R,LI X Y,YAN Y Y,et al.. Detection method of multi-target recognition of potato based on fusion of hyperspectral imaging and spectral information[J]. Trans. Chin. Soc. Agric. Eng., 2015,31(16):258-263. (in Chinese)

DONG J L,GUO W C,WANG Z W,et al.. Nondestructive determination of soluble solids content of Fuji apples produced in different areas and bagged with different materials during ripening[J]. Food Anal. Methods, 2016,9(5):1087-1095.

GUO W C,ZHAO F,DONG J L. Nondestructive measurement of soluble solids content of kiwifruits using near-infrared hyperspectral imaging[J]. Food Anal. Methods, 2016,9(1):38-47.

NOGALES-BUENO J,HERNNDEZ-HIERRO J M,RODRGUEZ-PULIDO F J,et al.. Determination of technological maturity of grapes and total phenolic compounds of grape skins in red and white cultivars during ripening by near infrared hyperspectral image:a preliminary approach[J]. Food Chem., 2014,152:586-591.

ARANA I,JARN C,ARAZURI S. Maturity,variety and origin determination in white grapes (Vitis vinifera L.) using near infrared reflectance technology[J]. J. Near Infrared Spectrosc., 2005,13(6):349-357.

BAIANO A,TERRACONE C,PERI G,et al.. Application of hyperspectral imaging for prediction of physico-chemical and sensory characteristics of table grapes[J]. Comput. Electron. Agric., 2012,87:142-151.

李龙,彭彦昆,李永玉,等. 基于纹理和梯度特征的苹果伤痕与果梗/花萼在线识别[J]. 农业机械学报, 2018,49(11):328-335. LI L,PENG Y K,LI Y Y,et al.. Online identification of apple scarring and stems/calyxes based on texture and edge gradient features[J]. Trans. Chin. Soc. Agric. Mach., 2018,49(11):328-335. (in Chinese)

DONG J L,GUO W C. Nondestructive determination of apple internal qualities using near-infrared hyperspectral reflectance imaging[J]. Food Anal. Methods, 2015,8(10):2635-2646.

王键,汪六三,王儒敬,等. 基于优选波长的复合肥总氮含量可见/近红外光谱分析[J]. 发光学报, 2018,39(12):1785-1791. WANG J,WANG L S,WANG R J,et al.. Analysis of total nitrogen in compound fertilizers by VIS-NIR spectroscopy[J]. Chin. J. Lumin., 2018,39(12):1785-1791. (in Chinese)

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]. Trans. Chin. Soc. Agric. Eng., 2018,34(16):148-154. (in Chinese)

任迎春,刘贵珊,张晶晶,等. 不同贮藏温度下滩羊肉pH值的近红外高光谱动力学模型建立[J]. 发光学报, 2019,40(3):396-403. REN Y C,LIU G S,ZHANG J J,et al.. Near-infrared hyperspectral kinetic models for the pH of tan mutton at different storage temperatures[J]. Chin. J. Lumin., 2019,40(3):396-403. (in Chinese)

浏览量

250

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

可见/近红外高光谱成像技术对长枣中葡萄糖含量的无损检测

高光谱成像结合SIS与RFS的蓝莓腐烂病检测

基于高光谱成像技术的土壤水分机理研究及模型建立

基于高光谱成像提取苹果糖度与硬度最佳波长

基于高光谱漫透射成像可视化检测脐橙可溶性固形物