Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging

  • Sara Sharifzadeh
  • Line H. Clemmensen
  • Hanne Løje
  • Bjarne K. Ersbøll
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7944)


Multispectral imaging is increasingly being used for quality assessment of food items due to its non-invasive benefits. In this paper, we investigate the use of multispectral images of pre-fried carrots, to detect changes over a period of 14 days. The idea is to distinguish changes in quality from spectral images of visible and NIR bands. High dimensional feature vectors were formed from all possible ratios of spectral bands in 9 different percentiles per piece of carrot. We propose to use a multiple hypothesis testing technique based on the Benjamini-Hachberg (BH) method to distinguish possible significant changes in features during the inspection days. Discrimination by the SVM classifier supported these results. Additionally, 2-sided t-tests on the predictions of the elastic-net regressions were carried out to compare our results with previous studies on fried carrots. The experimental results showed that the most significant changes occured in day 2 and day 14.


Multispectral imaging Multiple hypothesis testing Segmentation Food quality assessment SVM classification Elastic-net regression 


  1. 1.
    Adler-Nissen, J.: The Continuous Wok - a New Unit Operation in Industrial Food Processes. Food Process Engine 25, 435–453 (2002)CrossRefGoogle Scholar
  2. 2.
    Adler-Nissen, J.: Continuous Wok-Frying of Vegetables. Process parameters influencing scale up and product quality. Food Engineering 83, 54–60 (2007)CrossRefGoogle Scholar
  3. 3.
    Bao, H.N.D., Arason, S., Porarinsdottir, K.A.: Effects of Dry Ice and Superchilling onQuality and Shelf Life of Arctic Charr (SalvelinusAlpinus) Fillets. Food Engineering 3(3), art.7 (2007)Google Scholar
  4. 4.
    Adler-Nissen, J., Akkerman, R., Frosch, S., Grunow, M., Løje, H., Risum, J., Wang, Y., Ørnholt- Johansson, G.: Improving the supplychain and foodquality ofprofessionallyprepared meals. Trends in Food Science & Technology 29, 74–79 (2013)CrossRefGoogle Scholar
  5. 5.
    Løje, H., Dissing, S.B., Clemmensen, H.L., Ersbøll, K.B., Adler-Nissen, J.: Multispectral Imaging of Wok Fried Vegetables. In: 18th Scandinavian Workshop on Imaging Food Quality, Technical Report, Ystad, pp. 59–62 (2011)Google Scholar
  6. 6.
    Dissing, S.B., Clemmensen, H.L., Løje, H., Ersbøll, K.B., Adler-Nissen, J.: Temporal Reflectance Changes in Vegetables. In: 12th IEEE InternationalWorkshop on Computer Vision, pp. 1917–1922. IEEE Press, Kyoto (2009)Google Scholar
  7. 7.
    Clemmensen, H.L., Dissing, S.B., Hyldig, G., Løje, H.: Multispectral Imaging of Wok fried vegetables. Imaging Science and Technology 56(2), 20404-1-6 (2012)Google Scholar
  8. 8.
    Dudoit, S., Shaffer, P.J., Boldrick, C.J.: Multiple Hypothesis Testing in Microarray Experiments. Statist. Sci. 18, 71–103 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Diz, A.P., Carvajal-Rodríguez, A., Skibinski, D.O.F.: MultipleHypothesisTesting in Proteomics: a Strategy for Experimental Work. Molecular & Cellular Proteomics 10, M110.004374 (2011)Google Scholar
  10. 10.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, New York (2009)zbMATHCrossRefGoogle Scholar
  11. 11.
    Benjamini, Y., Hochberg, Y.: Controlling the False Discovery Rate: a Practical and Powerful Approach to Multiple Testing. Royal Statistical Society 57, 289–300 (1995)MathSciNetzbMATHGoogle Scholar
  12. 12.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Transactions on Systems,Man, and Cybernetics 9, 62–66 (1979)CrossRefGoogle Scholar
  13. 13.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Prentice Hall, New Jersey (2001)Google Scholar
  14. 14.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 27:1–27:27 (2011), Software available at

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sara Sharifzadeh
    • 1
  • Line H. Clemmensen
    • 1
  • Hanne Løje
    • 2
  • Bjarne K. Ersbøll
    • 1
  1. 1.Department of Applied Mathematics and Computer ScienceTechnical University of DenmarkDenmark
  2. 2.National Food InstituteTechnical University of DenmarkDenmark

Personalised recommendations