Food Analytical Methods

, Volume 12, Issue 9, pp 1988–1997 | Cite as

A Clustering-Based Partial Least Squares Method for Improving the Freshness Prediction Model of Crucian Carps Fillets by Hyperspectral Image Technology

  • Xue Wang
  • Mohammad Russel
  • Yiwen Zhang
  • Junbo Zhao
  • Yituo Zhang
  • Jiajia ShanEmail author


Hyperspectral imaging technology (HSI) is able to visualize the distribution map of chemicals in samples in combination with a developed prediction model. Generally, prediction models are established based on the spectrum and the chemical reference averagely calculated/measured from the sole area covering the sample. However, uneven chemical distribution is widely observed in the individual sample. The uneven distribution of chemicals may result in the unspecific match between the spectrum and chemical reference, which were averagely achieved from the non-homogeneous sample, leading to low robustness model. The aim of this work was to improve the performance of the freshness prediction models of fillets by eliminating the effect of uneven chemical distribution in each fillet. This study proposed a clustering-based partial least squares (C-PLS) algorithm, which firstly divided a non-homogeneous fillet into several relatively homogeneous sub-pieces using cluster analysis. Spectra and freshness indices were averagely acquired from the sub-pieces respectively, aiming to find a more specific match between the spectra and chemical indices. Compared with the partial least squares regression model, C-PLS model performed a higher coefficient of determination of cross-validation for the prediction of total volatile basic nitrogen (TVB-N), pH, and water holding capacity (WHC) of the fillet, which would be a benefit for precisely monitoring fish quality online.


Cluster analysis Hyperspectral image Fillets Freshness Models improvement 



The authors thanks National Natural Science Foundation of China [grant number: 31701691]; the Fundamental Research Funds for the Central Universities [DUT17RC (4)41]; and Open Foundation of State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences [grant number: SKLECRA2017OFP02] for the financial support.

Compliance with Ethical Standards

Conflict of Interest

Xue Wang declares that there is no conflict of interest. Mohammad Russel declares that there is no conflict of interest. Yiwen Zhang declares that there is no conflict of interest. Junbo Zhao declares that there is no conflict of interest. Jiajia Shan declares that there is no conflict of interest.

Ethical Approval

All applicable international, national, or institutional guidelines for the care and use of animals were followed.

Informed Consent

Not applicable.

Supplementary material

12161_2019_1541_MOESM1_ESM.docx (28 kb)
ESM 1 (DOCX 27 kb)


  1. Araujo MCU, Saldanha TCB, Galvao RKH, Yoneyama T, Chame HC, Visani V (2001) The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemom Intell Lab Syst 57(2):65–73CrossRefGoogle Scholar
  2. Barbin DF, ElMasry G, Sun DW, Allen P (2012) Predicting quality and sensory attributes of pork using near-infrared hyperspectral imaging. Anal Chim Acta 719:30–42CrossRefPubMedGoogle Scholar
  3. Barbin DF, ElMasry G, Sun DW, Allen P (2013) Non-destructive determination of chemical composition in intact and minced pork using near-infrared hyperspectral imaging. Food Chemistry 138 (2-3):1162-1171Google Scholar
  4. Cao LP, Rasco BA, Tang JM, Niu LH, Lai KQ, Fan YX, Huang YQ (2016) Effects of freshness on the cook loss and shrinkage of grass carp (Ctenopharyngodon idellus) fillets following pasteurization. Int J Food Prop 19(10):2297–2306CrossRefGoogle Scholar
  5. Chen X, Chen CG, Zhou YZ, Li PJ, Ma F, Nishiumi T, Suzuki A (2014) Effects of high pressure processing on the thermal gelling properties of chicken breast myosin containing kappa-carrageenan. Food Hydrocoll 40:262–272CrossRefGoogle Scholar
  6. Cheng JH, Da-Wen Sun, Xin-An Zeng, Hong-Bin Pu (2014) Non-destructive and rapid determination of TVB-N content for freshness evaluation of grass carp (Ctenopharyngodon idella) by hyperspectral imaging. Innovative Food Science & Emerging Technologies 21:179-187Google Scholar
  7. Cheng JH, Sun DW, Qu JH, Pu HB, Zhang XC, Song ZX, Chen XH, Zhang H (2016) Developing a multispectral imaging for simultaneous prediction of freshness indices during chemical spoilage of grass carp fish fillet. J Food Eng 182:9–17CrossRefGoogle Scholar
  8. Dai Q, Sun DW, Xiong ZJ, Cheng JH, Zeng XA (2014) Recent advances in data mining techniques and their applications in hyperspectral image processing for the food industry. Compr Rev Food Sci Food Saf 13(5):891–905CrossRefGoogle Scholar
  9. ElMasry G, Wold JP (2008) High-speed assessment of fat and water content distribution in fish fillets using online imaging spectroscopy. J Agric Food Chem 56(17):7672–7677CrossRefPubMedGoogle Scholar
  10. Feng CH, Makino Y, Yoshimura M, Thuyet DQ, Martin JFG (2018) Hyperspectral imaging in tandem with R statistics and image processing for detection and visualization of pH in Japanese big sausages under different storage conditions. J Food Sci 83(2):358–366CrossRefPubMedGoogle Scholar
  11. He H, Wu D, Sun DW (2014) Rapid and non-destructive determiantion of drip loss and pH distribution in farmed Atlantic salmon (Salmo salar) fillets using visiable and near infrared (Vis-NIR) hyperspectral imaging. Food Chem 156:394–401CrossRefPubMedGoogle Scholar
  12. Huang ZX (1998) Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Min Knowl Disc 2(3):283–304CrossRefGoogle Scholar
  13. Kristensen L, Purslow PP (2001) The effect of ageing on the water-holding capacity of pork: role of cytoskeletal proteins. Meat Sci 58(1):17–23CrossRefPubMedGoogle Scholar
  14. Lee H, Kim MS, Lee WH, Cho BK (2018) Determination of the total volatile basic nitrogen (TVB-N) content in pork meat using hyperspectral fluorescence imaging. Sensors Actuators B Chem 259:532–539CrossRefGoogle Scholar
  15. Liao YT, Fan YX, Cheng F (2010) On-line prediction of fresh pork quality using visible/near-infrared reflectance spectroscopy. Meat Sci 86(4):901–907CrossRefPubMedGoogle Scholar
  16. Ma J, Sun DW, Qu JH, Pu HB (2017) Prediction of textural changes in grass carp fillets as affected by vacuum freeze drying using hyperspectral imaging based on integrated group wavelengths. Lwt-Food Science And Technology 82:377–385CrossRefGoogle Scholar
  17. Olsson GB, Ofstad R, Lodemel JB, Olsen RL (2003) Changes in water-holding capacity of halibut muscle during cold storage. Lebensmittel-Wissenschaft Und-Technologie-Food Science and Technology 36(8):771–778CrossRefGoogle Scholar
  18. Qin JW, Kim MS, Chao KL, Chan DE, Delwiche SR, Cho BK (2017) Line-scan hyperspectral imaging techniques for food safety and quality applications. Applied Sciences-Basel 7(2):22Google Scholar
  19. Ravikanth L, Jayas DS, White NDG, Fields PG, Sun DW (2017) Extraction of spectral information from hyperspectral data and application of hyperspectral imaging for food and agricultural products. Food Bioprocess Technol 10(1):1–33CrossRefGoogle Scholar
  20. Ritthiruangdej P, Kasemsumran S, Suwonsichon T, Haruthaithanasan V, Thanapase W, Ozaki Y (2005) Determination of total nitrogen content, pH, density, refractive index, and brix in Thai fish sauces and their classification by near-infrared spectroscopy with searching combination moving window partial least squares. Analyst 130(10):1439–1445CrossRefPubMedGoogle Scholar
  21. Rodrigues BL, da Costa MP, Frasao BD, da Silva FA, Marsico ET, Alvares TD, Conte CA (2017) Instrumental texture parameters as freshness indices in five farmed Brazilian freshwater fish species. Food Anal Methods 10(11):3589–3599CrossRefGoogle Scholar
  22. Ruiz-Capillas C, Moral A (2005) Sensory and biochemical aspects of quality of whole bigeye tuna (Thunnus obesus) during bulk storage in controlled atmospheres. Food Chem 89(3):347–354CrossRefGoogle Scholar
  23. Shan J, Wang X, Russel M, Zhao J, Zhang Y (2018) Comparisons of fish morphology for fresh and frozen-thawed crucian carp quality assessment by hyperspectral imaging technology. Food Anal Methods 11(6):1701–1710CrossRefGoogle Scholar
  24. Siche R, Vejarano R, Aredo V, Velasquez L, Saldana E, Quevedo R (2016) Evaluation of food quality and safety with hyperspectral imaging (HSI). Food Eng Rev 8(3):306–322CrossRefGoogle Scholar
  25. Sun Y, Gu XZ, Sun K, Hu HJ, Xu M, Wang ZJ, Tu K, Pan LQ (2017) Hyperspectral reflectance imaging combined with chemometrics and successive projections algorithm for chilling injury classification in peaches. Lwt-Food Science And Technology 75:557–564CrossRefGoogle Scholar
  26. Tarabalka Y, Benediktsson JA, Chanussot J (2009) Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques. IEEE Trans Geosci Remote Sens 47(8):2973–2987CrossRefGoogle Scholar
  27. Washburn KE, Stormo SK, Skjelvareid MH, Heia K (2017) Non-invasive assessment of packaged cod freeze-thaw history by hyperspectral imaging. J Food Eng 205:64–73CrossRefGoogle Scholar
  28. Wold JP, Kermit M, Segtnan VH (2016) Chemical imaging of heterogeneous muscle foods using near-infrared hyperspectral imaging in transmission mode. Appl Spectrosc 70(6):953–961CrossRefPubMedGoogle Scholar
  29. Wu D, Sun DW (2013) Application of visiable and near infrared hypespectral imaging for non-invasively measuring distribution of water holding capacity in salmon flesh. Talanta 116:266–276CrossRefPubMedGoogle Scholar
  30. Yan Q, Ding Y, Xia Y, Chong YW, Zheng CH (2017) Class probability propagation of supervised information based on sparse subspace clustering for hyperspectral images. Remote Sens 9(10):1–18CrossRefGoogle Scholar
  31. Yang Q, Sun DW, Cheng W (2017) Development of simplified models for nondestructive hyperspectral imaging monitoring of TVB-N contents in cured meat during drying process. Journal of Food Engineering 192:53-60Google Scholar
  32. Yang YC, Sun DW, Wang NN (2015) Rapid detection of browning levels of lychee pericarp as affected by moisture contents using hyperspectral imaging. Comput Electron Agric 113:203–212CrossRefGoogle Scholar
  33. Yang Y, Zhuang H, Yoon SC, Wang W, Jiang H, Jia B, Li C (2018) Quality assessment of intact chicken breast fillets using factor analysis with Vis/NIR spectroscopy. Food Anal Methods 11:1356–1366CrossRefGoogle Scholar
  34. Yao J, Zhou Y, Chen X, Ma F, Li PJ, Chen CG (2018) Effect of sodium alginate with three molecular weight forms on the water holding capacity of chicken breast myosin gel. Food Chem 239:1134–1142CrossRefPubMedGoogle Scholar
  35. Zang JH, Xu YS, Xia WS, Jiang QX (2017) The impact of desmin on texture and water-holding capacity of ice-stored grass carp (Ctenopharyngodon idella) fillet. Int J Food Sci Technol 52(2):464–471CrossRefGoogle Scholar
  36. Zhang LN, Li X, Lu W, Shen HX, Luo YK (2011) Quality predictive models of grass carp (Ctenopharyngodon idellus) at different temperatures during storage. Food Control 22(8):1197–1202CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Food and EnvironmentDalian University of TechnologyPanjinChina

Personalised recommendations