基于高光谱成像提取苹果糖度与硬度最佳波长

冯迪; 纪建伟; 张莉; 刘思伽; 田有文

doi:10.3788/fgxb20173806.0799

您当前的位置：

首页 >

文章列表页 >

基于高光谱成像提取苹果糖度与硬度最佳波长

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 基于高光谱成像提取苹果糖度与硬度最佳波长
- Optimal Wavelengths Extraction of Apple Brix and Firmness Based on Hyperspectral Imaging
- 发光学报 2017年38卷第6期页码：799-806
- 作者机构：
  
  1. 沈阳农业大学信息与电气工程学院, 辽宁沈阳 110866
  2. 辽宁广播电视台,辽宁沈阳,110004
  3. 辽宁广播电视传输发射中心,辽宁沈阳,110004
- 作者简介：
- 基金信息：
  
  辽宁省大型仪器设备共享服务项目（LNDY201501003）();沈阳市大型仪器设备共享服务专项项目（F15-166-4-00）资助()
- DOI：10.3788/fgxb20173806.0799
  中图分类号： S126;TP391.44
- 纸质出版日期：2017-6-5，
  
  收稿日期：2016-12-17，
  
  修回日期：2017-3-8，
扫描看全文
冯迪, 纪建伟, 张莉等. 基于高光谱成像提取苹果糖度与硬度最佳波长[J]. 发光学报, 2017,38(6): 799-806

FENG Di, JI Jian-wei, ZHANG Li etc. Optimal Wavelengths Extraction of Apple Brix and Firmness Based on Hyperspectral Imaging[J]. Chinese Journal of Luminescence, 2017,38(6): 799-806
冯迪, 纪建伟, 张莉等. 基于高光谱成像提取苹果糖度与硬度最佳波长[J]. 发光学报, 2017,38(6): 799-806 DOI： 10.3788/fgxb20173806.0799.

FENG Di, JI Jian-wei, ZHANG Li etc. Optimal Wavelengths Extraction of Apple Brix and Firmness Based on Hyperspectral Imaging[J]. Chinese Journal of Luminescence, 2017,38(6): 799-806 DOI： 10.3788/fgxb20173806.0799.

摘要

利用高光谱成像技术提取可同时检测苹果糖度与硬度的最佳波长。首先双面采集苹果的高光谱图像，获取亮度相近感兴趣区域（ROIs）的反射波形，采用二阶导数结合标准正态变量（SD+SNV）的方法平滑波形，测试ROIs的糖度与硬度;之后采用连续投影算法（SPA）提取两项指标的特征波长，根据特征波长的分布提出二次连续投影算法，结合波形集特征与两次投影结果确定不同取样面的最佳波长;最后采用遗传算法开发神经网络（GA-BP）建立预测模型，双面取样波长（543 nm和674 nm）效果最优，糖度相关系数（

）为0.847 6，均方误差（MSE）为3.32;硬度

为0.793 8，MSE为9.6。结果表明，相同波长信息可以检测苹果糖度与硬度。

Abstract

Hyperspectral imaging technology was used to extract the optimal wavelength for apple brix and firmness test. Firstly

the hyperspectral images of apples were acquired from double-sided sampling. The reflection waveforms of the regions of interest (RIOs) with similar brightness were acquired and smoothed by the second derivation and standard normal variate (SD+SNV) method. The brix and firmness values of RIOs were also tested. Then

the characteristic wavelengths of two indicators were extracted by using the successive projections agorithm(SPA). According to the distribution of characteristics wavelengths

two times SPA was proposed. Combined the feature of waveforms and the results of two projections

the optimal wavelengths of different sampling facets were determined. Finally

the genetic algorithm for back propagation(GA-BP) was used to build the prediction model. The best results were obtained from the double-sided sampling wavelengths (543 nm and 674 nm). The correlation coefficient of brix (

) is 0.847 6 and the mean square error (MSE) is 3.32

and for the firmness

is 0.793 8 and MSE is 9.6. The results show that the brix and firmness can be detected by the same wavelength information.

关键词

高光谱成像苹果最佳波长二次连续投影算法遗传算法开发神经网络

Keywords

hyperspectral imagingappleoptimal wavelengthtwo times SPAGA-BP

references

孙梅, 陈兴海, 张恒, 等. 高光谱成像技术的苹果品质无损检测[J]. 红外与激光工程, 2014, 43(4):1272-1277. SUN M, CHEN X H, ZHANG H, et al.. Nondestructive inspect of apple quality with hyperspectral imaging[J]. Infrared Laser Eng., 2014, 43(4):1272-1277. (in Chinese)

吴龙国, 何建国, 贺晓光, 等. 高光谱图像技术在水果无损检测中的研究进展[J]. 激光与红外, 2013, 43(9):990-996. WU L G, HE J G, HE X G, et al.. Research progress of hyperspectral imaging technology in non-destructive detection of fruit[J]. Laser Infrared, 2013, 43(9):990-996. (in Chinese)

宫元娟, 周铁, 屈亚堃, 等. 寒富苹果品质无损检测光谱信息在线分析[J]. 沈阳农业大学学报, 2014, 45(6):708-713. GONG Y J, ZHOU T, QU Y K, et al.. Online analysis on Hanfu apple quality spectral information based on NDT[J]. J. Shenyang Agric. Univ., 2014, 45(6):708-713. (in Chinese)

汪泊锦, 黄敏, 朱启兵, 等. 基于高光谱散射图像技术的UVE-LLE苹果粉质化分类[J]. 光子学报, 2011, 40(8):1132-1136. WANG B J,HUANG M,ZHU Q B,et al.. UVE-LLE classification of apple mealiness based on hyperspectral scattering image[J]. Acta Photon. Sinica, 2011, 40(8):1132-1136. (in Chinese)

黄鸿, 郑新磊, 罗甫林. 融合加权均值滤波与流形重构保持嵌入的高光谱影像分类[J]. 光子学报, 2016, 45(10):1030001. HUANG H, ZHENG X L, LUO F L. Hyperspectral image classification with combination of weighted mean filter and manifold reconstruction preserving embedding[J]. Acta Photon. Sinica, 2016, 45(10):1030001. (in Chinese)

郭志明, 黄文倩, 彭彦昆, 等. 高光谱图像感兴趣区域对苹果糖度模型的影响[J]. 现代食品科技, 2014, 30(8):59-63. GUO Z M, HUANG W Q, PENG Y K, et al.. Impact of region of interest selection for hyperspectral imaging and modeling of sugar content in apple[J]. Mod. Food Sci. Technol., 2014, 30(8):59-63. (in Chinese)

郭俊先, 饶秀勤, 程国首, 等. 基于高光谱成像技术的新疆冰糖心红富士苹果分级和糖度预测研究[J]. 新疆农业大学学报, 2012, 35(1):78-86. GUO J X, RAO X Q, CHENG G S, et al.. Prediction of the sugar degree and grading of Xinjiang Fuji apple by hyper-spectral imaging techniques[J]. J. Xinjiang. Agric. Univ., 2012, 35(1):78-86. (in Chinese)

ZHAO J W, CHEN Q S, SARITPORN V, et al.. Determination of apple firmness using hyperspectral imaging technique and multivariate calibrations[J]. Trans. CSAE, 2009, 25(11):226-231.

WANG S, HUANG M, ZHU Q B. Model fusion for prediction of apple firmness using hyperspectral scattering image[J]. Comput. Electron. Agric., 2012, 80:1-7.

MENDOZA F, Lu R F, ARIANA D, et al.. Integrated spectral and image analysis of hyperspectral scattering data for prediction of apple fruit firmness and soluble solids content[J]. Postharvest Biol. Technol., 2011, 62(2):149-160.

PENG Y K, LU R F. Analysis of spatially resolved hyperspectral scattering images for assessing apple fruit firmness and soluble solids content[J]. Postharvest Biol. Technol., 2008, 48(1):52-62.

单佳佳, 吴建虎, 陈菁菁, 等. 基于高光谱成像的苹果多品质参数同时检测[J]. 光谱学与光谱分析, 2010, 30(10):2729-2733. SHAN JJ, WU J H, CHEN J J, et al.. Rapid nondestructive detection of apple quality attributes using hyperspectral scattering images[J]. Spectrosc. Spect. Anal., 2010, 30(10):2729-2733. (in Chinese)

万相梅, 黄敏, 朱启兵. 基于高光谱散摄图像的苹果压缩硬度和汁液含量无损检测[J]. 食品工业科技, 2012, 33(6):71-74. WAN X M, HUANG M, ZHU Q B. Non-destructive detection for compression hardness and juiciness in apple based on hyperspectral scattering image[J]. Sci. Technol. Food Ind., 2012, 33(6):71-74. (in Chinese)

张巍. 基于高光谱成像技术的蓝莓内部品质检测方法的研究[D]. 沈阳:沈阳农业大学, 2016:21-22. ZHANG W. Research on Blueberry Internal Quality Detection Method Based on Hyperspectral Imaging Technology. Shenyang:Shenyang Agricultural University, 2016:21-22. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于高光谱图像信息融合的红提糖度无损检测

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

基于高光谱漫透射成像可视化检测脐橙可溶性固形物