Multimedia Tools and Applications

, Volume 77, Issue 20, pp 27505–27516 | Cite as

The study on increasing the identification accuracy of waxed apples by hyperspectral imaging technology

  • Huiquan Wang
  • Haojie Zhu
  • Zhe ZhaoEmail author
  • Yanfeng Zhao
  • Jinhai WangEmail author


Hyperspectral imaging technology is applied to nondestructive quality determination of agricultural and food products. It has a greater advantage of combining spatial image and spectral measurement which can determine both external and internal quality of the product. To increase the classification accuracy and stability of the prediction model, the spectral correlation analysis of each pixel was used to determine quality of the sample’s hyperspectral image in this study. 400 hyperspectral image ROIs were extracted from 40 apples (20 apples with waxed and the other 20 apples without any waxed) were studied. Two effective wavelengths (806.85 nm, 1073.97 nm) were screened by spectral correlation analysis of pixels in 7 peak wave bands (639.90 nm, 806.85 nm, 973.80 nm, 1073.97 nm, 1197.99 nm, 1269.54 nm, 1441.26 nm). When the spectral correlation degree is less than 0.9 among all the pixels in the same sample, this sample data should be eliminated before inputting into the model training group. The least squares support vector machine (LS-SVM) model and BP neural network were used to establish the classification model between the hyperspectral image and waxed situation. The prediction result showed the classification accuracy was increased from 82% to 100% when the low-quality sample data for training were filtered by spectral correlation analysis. By evaluating the quality of the hyperspectral image measured, more reliable prediction results can be obtained, which can make the noninvasive discrimination of food safety come to the practice application sooner.


Hyperspectral image Correlation analysis Classification Waxed apples 



The authors gratefully acknowledge the support from the Tianjin Application Basis & Front Technology Study Programs (No. 14JCZDJC33100) & Chinese Postdoctoral Science Foundation No.61.


  1. 1.
    Bao Y, Chen N, He Y et al (2015) Rapid identification of coffee bean variety by near infrared hyperspectral imaging technology. Opt Precis Eng 23(2):349–355CrossRefGoogle Scholar
  2. 2.
    Baranowski P, Mazurek W, Wozniak J et al (2012) Detection of early bruises in apples using hyperspectral data and thermal imaging. J Food Eng 110(3):345–355CrossRefGoogle Scholar
  3. 3.
    Cao F, Wu D, Zheng J et al (2011) Study on pear damage detection based on visible-near infrared spectroscopy and multi-spectral imaging technique. Spectrosc Spectr Anal 31(4):920–923Google Scholar
  4. 4.
    Cheng B, Guo Z (2013) The research on the hyperspectral image inter-band correlation. Jounral of Daqing Normal University 33(6):35–37MathSciNetGoogle Scholar
  5. 5.
    Dull GG, Birth GS, Smittle DA et al (1989) Near infrared analysis of soluble solids in intact cantaloupe. J Food Sci 54(2):393–395CrossRefGoogle Scholar
  6. 6.
    Feng YZ, Sun DW (2012) Application of hyperspectral imaging in foodsafety inspection and control: a review. Crit Rev Food Sci Nutr 52:1039–1058CrossRefGoogle Scholar
  7. 7.
    Gao J, Zhang H, Kong W et al (2013) Non-spectral identification of waxed apple by hyperspectral imaging. Spectrosc Spectr Anal 33(7):1922–1926Google Scholar
  8. 8.
    Guo Y, Liang J, Min-Min L, Zheng-Yang Z (2012) Determination of. Organic Acids in Apple Fruits by HPLC 33(2):227–231Google Scholar
  9. 9.
    He Y, Li X (2006) Discrim inating varieties of waxberry using near infrared spectra. J Infrared Millimeter Waves 25(3):192–194MathSciNetGoogle Scholar
  10. 10.
    Lawrence KC, Yoon SC, Heitschmidt GW (2008) Imaging system with modified-pressure chamber for crack detection in shell eggs. Sens & Instrumen Food Qual 2(3):116–122CrossRefGoogle Scholar
  11. 11.
    Liu D, Sun D-W, Zeng X-A (2014) Recent advances in wavelength selection techniques for hyperspectral image processing in the food industry. Food Bioprocess Technol 7:307–323CrossRefGoogle Scholar
  12. 12.
    Liu Y, Bai Y, Qiu Z et al (2015) Hyperspectral Imaging Technology and Wavelength Selection Method for Nondestructive Detection of Mutton Adulteration. Journal of Hainan Normal University 28(3)Google Scholar
  13. 13.
    Meng Y, Zhang Y, Wang J et al (2014) Fast identification based on near infrared spectroscopy with the animal source of meat. Food Sci 35(6):156–158Google Scholar
  14. 14.
    Qin J, Chao K, Kim MS et al (2013) Hyperspectral and multispectral imaging for evaluating food safety and quality. J Food Eng 118(2):157–171CrossRefGoogle Scholar
  15. 15.
    Qin JW, Chao KL, Kim MS, Lu RF, Burks TF (2013) Hyperspectral and multispectral imaging for evaluating food safety and quality. J Food Eng 118:157–171CrossRefGoogle Scholar
  16. 16.
    Suykens JAK, Vandewalle J (1999) Least Squares Support Vector Machine Classifiers. Neural Process Lett 9(3):293–300CrossRefGoogle Scholar
  17. 17.
    Tian Y, Mu X, Cheng Y (2014) Study on Non-destructive Testing of Fruit Defects by Hyperspectral Imaging Progress. Agricultural Mechanization Research 6(1):1–5Google Scholar
  18. 18.
    Wang L, Cai LS, Lin Z et al (2010) Analysis of aroma compounds in white tea using headspace solid-phase micro-extraction and GC-MS. J Tea Sci 30(2):115–123Google Scholar
  19. 19.
    Wenqian H, Liping C, Jiangbo L et al (2013) Effective wavelengths determination for detection of slight bruises on apples based on hyperspectral imaging. Transactions of the CSAE 29(1):272–277Google Scholar
  20. 20.
    Wu D, Sun D-W, He Y (2012) Application of long-wave near infrared hyperspectral imaging for measurement of color distribution in salmon fillet. Innovative Food Sci Emerg Technol 16:361–372CrossRefGoogle Scholar
  21. 21.
    Xing J, Baerdemaeker JD (2005) Bruise detection on ‘Jonagold’ apples using hyperspectral imaging. Postharvest Biol Technol 37(2):152–162CrossRefGoogle Scholar
  22. 22.
    Xu S, Lu H, Zhou Z et al (2015) Hyperspectral and Electronic Nose Fusion Method for identification of mechanical damage of pomegranate. Journal of Agricultural Mechanization 46(7):214–219Google Scholar
  23. 23.
    You D, Jiang JB, Zhang Z et al (2016) Spectral Derivative Method for Detecting Minor Bruises on Apples. Fujian Journal of Agricultural Sciences 31(2):151–156Google Scholar
  24. 24.
    Zhang B, Huang W, Li J et al (2013) Hyperspectral imaging and PCA detection fruit damage and early decay. Infrared and Laser Engineering 42(2):279–283Google Scholar
  25. 25.
    Zhang B, Fan S, Li J et al (2015) Detection of Early Rottenness on Apples by Using Hyperspectral Imaging Combined with Spectral Analysis and Image Processing. Food Anal Methods 8(8):2075–2086CrossRefGoogle Scholar
  26. 26.
    Zhang B, Huang W, Liang G et al (2015) Computer vision detection of defective apples using automatic lightness correction and weighted RVM classifier. J Food Eng 146:143–151CrossRefGoogle Scholar
  27. 27.
    Zhao J, Liu J, Chen Q et al (2008) Detecting subtle bruiseson fruit swith hyperspectral imaging. Transactions of the Chinese Society for Agricultural Machinery 39(1):106–109Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Electronics and Information EngineeringTianjin Polytechnic UniversityTianjinChina
  2. 2.Tianjin Medical Electronic Treating-Technology Engineering CenterTianjinChina
  3. 3.Tianjin Key Laboratory of Optoelectronic Detection Technology and SystemTianjinChina

Personalised recommendations