Advertisement

Classification and weighing of sweet lime (Citrus limetta) for packaging using computer vision system

  • Vikas R. PhateEmail author
  • R. Malmathanraj
  • P. Palanisamy
Original Paper

Abstract

Weight is widely used as an important measure to study the physiology and agronomy for monitoring the fruit growth, grading, and packaging. The development of a computer vision system to measure the sweet lime fruit weight by relating the weight with its physical attributes is economically efficient than the mechanical online load cell used in the fruit sorting machines. In the present work, firstly a classification tree is developed using classification and regression tree algorithm to classify the fruits based on size. The average accuracy, sensitivity, specificity, and F score achieved are 98.16%, 94.01%, 98.51%, and 94.85% respectively. Secondly, parametric and non- parametric models are developed for predicting the weight of these classified fruits. A non-parametric model is developed using feed forward artificial neural network (FFANN) with error back propagation. The best topology is found among the fifty different FFANN configurations formed by varying the count of neurons in the hidden layer. Two parametric models are also developed using an approach of dimensional analysis (DA), and normal regression (NR). If the volume and the weight of the fruit have high correlation; then the bulk density of the fruit is fairly constant. This is the hypothesis used for developing the DA model. A lower value of mean square relative error and the remarkable value of Nash–Sutcliffe coefficient of efficiency indicate the superiority and the robustness of the proposed NR model in estimating the weight of the sweet lime fruits. Furthermore, an estimation uncertainty Theil_UII value which demonstrates the effectiveness and the credibility of the model’s estimation ability is used for performance evaluation.

Keywords

Dimensional analysis Normal regression Feed forward artificial neural network Image processing Classification Weight estimation 

Abbreviations

R2

Coefficient of determination

Wmes

Measured weight of sweet lime fruit (g)

i

Indexing variable

Vcal

Calculated volume of plastic ball (mm3)

Acal

Calculated area of plastic ball (mm2)

Perical

Calculated perimeter of plastic ball (mm)

CF

Conversion factor

L

Length of sweet lime (mm)

D2

Height of sweet lime (mm)

PeriHori and PeriVer

Perimeter of sweet lime in horizontal and vertical orientation respectively (mm)

Пi

Dimensionless group

NSE

Nash and Sutcliffe’s coefficient of efficiency

LR

Linear regression

West

Estimated weight of sweet lime (g)

NR

Normal regression

VWDS

Volume of sweet lime measured using water displacement method (mm3)

WDM

Water displacement method

D1avg

Average width of sweet lime (mm)

CART

Classification and regression tree

PA1 and PA2

Projected area of sweet lime in horizontal and vertical orientation respectively (mm2)

Notes

References

  1. 1.
    Horticultural Statistics at a Glance, Report, Horticulture Statistics Division, Dept. of Agric., Cooperation & Farmers Welfare, Ministry of Agric. & Farmers Welfare, Government of India (2017), http://www.indiaenvironmentportal.org.in/files/file/Horticulture%20At%20a%20Glance%202017.pdf. Accessed 30 May, 2018
  2. 2.
    M. Omid, M. Khojastehnazhand, A. Tabatabaeefar, J. Food Eng. 100, 2 (2010)  https://doi.org/10.1016/j.jfoodeng.2010.04.015 CrossRefGoogle Scholar
  3. 3.
    A. Tabatabaeefar, A. Rajabipour, Sci. Hortic. 105, 3 (2005).  https://doi.org/10.1016/j.scienta.2005.01.030 CrossRefGoogle Scholar
  4. 4.
    A.N. Lorestani, A. Tabatabaeefar, Int. Agrophys. 20 (2006)Google Scholar
  5. 5.
    S.M.A. Razavi, M. BahramParvar, Int. J. Food Eng. 3, 6 (2007).  https://doi.org/10.2202/1556-3758.1276 CrossRefGoogle Scholar
  6. 6.
    K. Schulze, M. Nagle, W. Spreer, B. Mahayothee, J. Muller, J. Comput. Electron. Agric. 114 (2015)  https://doi.org/10.1016/j.compag.2015.04.013
  7. 7.
    A.B. Koc, J. Postharvest Biol. Technol. 45, 3 (2007).  https://doi.org/10.1016/j.postharvbio.2007.03.010 CrossRefGoogle Scholar
  8. 8.
    M. Khanali, M.G. Varnamkhasti, A. Tabatabaeefar, H. Mobli, Int. Agrophys. 21 (2007)Google Scholar
  9. 9.
    S.H.M. Ashtiani, J.B. Motie, B. Emadi, M.H. Aghkhani, J. Food Sci. Technol. 51, 11 (2014).  https://doi.org/10.1007/s13197-012-0862-1 Google Scholar
  10. 10.
    A. Tabatabaeefar, A. Vefagh – A. Nematolahee, Rajabipour, J. Agric. Sci. Technol. 2, (2000)Google Scholar
  11. 11.
    R.A. Firouzjaei, S. Minaei, B. Beheshti, J. Food Meas. Charact. (2018)  https://doi.org/10.1007/s11694-018-9766-8 Google Scholar
  12. 12.
    G.V. Venkatesh, S.M. Iqbal, A. Gopal, D. Ganesan, Int. J. Food Prop. 18, 3 (2015)  https://doi.org/10.1080/10942912.2013.831444
  13. 13.
    C.M. Sabliov, D. Boldor, K.M. Keener, B.E. Farkas, Int. J. Food Prop. 5, 3 (2002)  https://doi.org/10.1081/JFP-120015498 CrossRefGoogle Scholar
  14. 14.
    T.Y. Wang, S.K. Nguang, J. Food Eng. 79, 3 (2007).  https://doi.org/10.1016/j.jfoodeng.2006.01.084 Google Scholar
  15. 15.
    A. Ziaratban, M. Azadbakht, A. Ghasemnezhad, J. Food Prop. 20, 4 (2017)  https://doi.org/10.1080/10942912.2016.1180533 Google Scholar
  16. 16.
    S.M. Goni, E. Purlis, V.O. Salvadori, J. Food Eng. 82,4 (2007)  https://doi.org/10.1016/j.jfoodeng.2007. 03.021
  17. 17.
    S. Sabzi, P. Javadikia, H. Rabani, A. Adelkhani, J. Meas. 46, 9 (2013)  https://doi.org/10.1016/j.measurement.2013.06.005 CrossRefGoogle Scholar
  18. 18.
    M. Sharifi, S. Rafiee, A. Keyhani, A. Jafari, H. Mobli, A. Rajabipour, A. Akram, Int. Agrophys. 21 (2007)Google Scholar
  19. 19.
    M.S. Iraji, J. Food Meas. Charact. (2018)  https://doi.org/10.1007/s11694-018-9913-2 Google Scholar
  20. 20.
    K. Vivek, S. Mishra, R.C. Pradhan, J. Food Meas. Charact. 12 (2018)  https://doi.org/10.1007/s11694-017-9708-x
  21. 21.
    H. Schenck Jr., Theories of Engineering Experimentation (McGraw-Hill Book Company, New York, 1961)CrossRefGoogle Scholar
  22. 22.
    N. Otsu, IEEE Trans. Syst. Man Cybern. SMC (1979)  https://doi.org/10.1109/TSMC. 4310076
  23. 23.
    I.M. Jamadar, D.P. Vakharia, J. Meas. (2016)  https://doi.org/10.1016/j.measurement.2016. 07.086Google Scholar
  24. 24.
    S. Shah, P. Shridhar, D. Gohil, Asian J. Pharm. 4, 3 (2010)Google Scholar
  25. 25.
    C.W. Dawson, R.J. Abrahart, L.M. See, J. Environ. Model. Softw. 22, 7 (2007).  https://doi.org/10.1016/j.envsoft.2006.06.008 Google Scholar
  26. 26.
    D.R. Legates, G.J. McCabe Jr., Water Resour. Res. 35, 1 (1999).  https://doi.org/10.1029/1998WR900 018CrossRefGoogle Scholar
  27. 27.
    J.E. Nash, J.V. Sutcliffe, J. Hydrol. 10, 3 (1970).  https://doi.org/10.1016/0022-1694(70)90255-6 Google Scholar
  28. 28.
    D.N. Moriasi, G.J. Arnold, M.W. Van Liew, R.L. Bingner, R.D. Harmel, T.L. Veith, Trans. ASABE 50, 3 (2007)  https://doi.org/10.13031/2013.23153 Google Scholar
  29. 29.
    F. Bliemel, J. Market. Res. 10, 4 (1973).  https://doi.org/10.2307/3149394 CrossRefGoogle Scholar

Copyright information

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

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringNational Institute of TechnologyTiruchirappalliIndia

Personalised recommendations