Food and Bioprocess Technology

, Volume 10, Issue 7, pp 1257–1264 | Cite as

An Open Source Conveyor Belt Prototype for Image Analysis-Based Rice Yield Determination

  • F. Antonucci
  • S. Figorilli
  • C. Costa
  • F. Pallottino
  • A. Spanu
  • P. Menesatti
Original Paper


The basic role of industrial rice milling is the transformation of paddy rice into white rice with good appearance while selecting the best quality grain for human consumption. In Italy, the commercial value of paddy rice is assessed calculating whole and free of defect kernel yield after processing. The determination is performed by laboratories utilizing a benchtop yield machine that carries out the husking and kernel bleaching. The aim of the study is the development of a pilot conveyor belt (grain coulter), based on image analysis, to increase the reliability of laboratory yield estimation (discrimination of paddy and white grains). The tests regard rice grains belonging to 26 different genotypes of rice grown in Sardinia (Italy). The low-cost prototype based on open source technologies that aim to substitute the current subjective estimation made by eye with an industrial like optically based one. The method is based on the image analysis and extracts three main qualitative attributes: shape, size (i.e., Fourier descriptors and basic morphometry) and appearance (color), and the use of a multivariate classification technique (i.e., partial least squares discriminant analysis). The models discriminated samples of paddy or white rice for each genotype considered (26 models) and for all the genotypes considered together (1 model). For all the 27 models, the mean sensitivities and specificities were very high, ranging from 99 to 100%, while the mean classification errors were very low. The mean percentage of correct classification in the test set was equal to 99.99% for the “unique model” (i.e., paddy VS white rice) and 100% for the 26 single genotype models. The proposed system appears to be useful not only for paddy and white rice discrimination but also as a flexible apparatus for analyzing many other agro-food products. Indeed, the algorithm was used on other food products, such as red hot chili peppers for other discrimination purposes.


Rice yield Image analysis Grain coulter Fourier descriptors Partial least squares discriminant analysis Quality control 



This work was funded by the Italian Ministry of Agriculture, Food and Forestry Policies (MiPAAF), as part of the projects “POLORISO” (D.M. 5337 of December 5th 2011). Authors would like to thank Mr. Stefano Benigni for his help in the preparation of rice samples.


  1. Abbas, A., Murtaza, S., Aslam, F., Khawar, A., Rafique, S., & Naheed, S. (2011). Effect of processing on nutritional value of Rice (Oryza sativa). World Journal of Medical Sciences, 6(2), 68–73.Google Scholar
  2. Antonucci, F., Pallottino, F., Costa, C., Gazza, L., Bellato, S., & Menesatti, P. (2014). A flexible, laboratory scale and image analysis based equipment to assess rice quality classes. Journal of Food Science and Nutrition, 43(1), 37–47.Google Scholar
  3. Bangphan S, Bangphan P, Lee S, Jomjunyong S & Phanphet S (2009). The optimal millings condition of the quartz rice polishing cylinder using response surface methodology. Proceedings of the World Congress on Engineering, Vol (I) WCE, 1–3.Google Scholar
  4. Bookstein, F. L. (1989). Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 567–585.CrossRefGoogle Scholar
  5. Chong, I. G., & Jun, C. H. (2005). Performance of some variable selection methods when multicollinearity is present. Chemometrics and Intelligent Laboratory Systems, 78(1), 103–112.CrossRefGoogle Scholar
  6. Corrêa, P. C., da Silva, F. S., Jaren, C., Afonso Júnior, P. C., & Arana, I. (2007). Physical and mechanical properties in rice processing. Journal of Food Engineering, 79(1), 137–142.CrossRefGoogle Scholar
  7. Costa, C., Antonucci, F., Boglione, C., Menesatti, P., Vandeputte, M., & Chatain, B. (2013b). Automated sorting for size, sex and skeletal anomalies of cultured seabass using external shape analysis. Aquacultural Engineering, 52, 58–64.CrossRefGoogle Scholar
  8. Costa, C., Antonucci, F., Menesatti, P., Pallottino, F., Boglione, C., & Cataudella, S. (2013a). An advanced colour calibration method for fish freshness assessment: A comparison between standard and passive refrigeration modalities. Food and Bioprocess Technology, 6, 2190–2195.CrossRefGoogle Scholar
  9. Costa, C., Antonucci, F., Pallottino, F., Aguzzi, J., Sun, D. W., & Menesatti, P. (2011). Shape analysis of agricultural products: A review of recent research advances and potential application to computer vision. Food and Bioprocess Technology, 4, 673–692.CrossRefGoogle Scholar
  10. Costa, C., Negretti, P., Vandeputte, M., Pallottino, F., Antonucci, F., Aguzzi, J., Bianconi, G., & Menesatti, P. (2014). Innovative automated landmark detection for food processing: The backwarping approach. Food and Bioprocess Technology, 7, 2291–2298.CrossRefGoogle Scholar
  11. de Jong, S. (1993). SIMPLS: An alternative approach to partial least squares regression. Chemometrics and Intelligent Laboratory Systems, 18(3), 251–263.CrossRefGoogle Scholar
  12. Enterisi (2016). (last access 29/11/2016)
  13. Faostat (2015). (last access 29/11/2016)
  14. Febbi, P., Menesatti, P., Costa, C., Pari, L., & Cecchini, M. (2015). Automated determination of poplar chip size distribution based on combined image and multivariate analyses. Biomass & Bioenergy, 73, 1–10.CrossRefGoogle Scholar
  15. Forina, M., Oliveri, P., Lanteri, S., & Casale, M. (2008). Class-modeling techniques, classic and new, for old and new problems. Chemometrics and Intelligent Laboratory Systems, 93(2), 132–148.CrossRefGoogle Scholar
  16. Infantino, A., Aureli, G., Costa, C., Taiti, C., Antonucci, F., Menesatti, P., Pallottino, F., De Felice, S., D’Egidio, M. G., & Mancuso, S. (2015). Potential application of PTR-TOFMS for the detection of deoxynivalenol (DON) in durum wheat. Food Control, 57, 96–104.CrossRefGoogle Scholar
  17. ISO 7301 (1988). Rice-specification. ISO 7301. Geneva, Switzerland. 1–12.Google Scholar
  18. Kennard, R. W., & Stone, L. A. (1969). Computer aided design of experiments. Technometrics, 11(1), 137–148.CrossRefGoogle Scholar
  19. Kittler, J., & Illingworth, J. (1986). Minimum error thresholding. Pattern Recognition, 19(1), 41–47.CrossRefGoogle Scholar
  20. Lin, P., Chen, Y., & He, Y. (2012). Identification of broken rice kernels using image analysis techniques combined with velocity representation method. Food and Bioprocess Technology, 5(2), 796–802.CrossRefGoogle Scholar
  21. Ma, J., Sun, D. W., Qu, J. H., Liu, D., Pu, H., Gao, W. H., & Zeng, X. A. (2016). Applications of computer vision for assessing quality of Agri-food products: A review of recent research advances. Critical Reviews in Food Science and Nutrition, 56(1), 113–127.CrossRefGoogle Scholar
  22. Menesatti, P., Angelini, C., Pallottino, F., Antonucci, F., Aguzzi, J., & Costa, C. (2012). RGB color calibration for quantitative image analysis: The “3D thin-plate spline” warping approach. Sensors, 12, 7063–7079.CrossRefGoogle Scholar
  23. Miller, B. S., Lee, M. S., & Rousser, R. (1979). A rapid, objective method to measure the degree of milling of rice. Cereal Chemistry, 56, 172–180.Google Scholar
  24. Minkara, M. Y., Lawson, T. B., Breitenbeck, G. A., & Cochran, B. J. (1998). Cocomposting of crawfish and agricultural processing by-products. Compost Science & Utilization, 6(1), 67–74.CrossRefGoogle Scholar
  25. Pallottino, F., Menesatti, P., Antonucci, F., Figorilli, S., Proto, A. R., & Costa, C. (2016). Image analysis based open source conveyor belt prototype for wood pellet and chip quality assessment. Contemporary Engineering Sciences, 9(23), 1105–1112.CrossRefGoogle Scholar
  26. Pomeranz, Y., & Webb, B. D. (1985). Rice hardness and functional properties. Cereal Foods World, 30(11), 784–790.Google Scholar
  27. Sabatier, R., Vivein, M., & Amenta, P. (2003). Two approaches for discriminant partial least square. In M. Schader, W. Gaul, & M. Vichi (Eds.), Between data science and applied data analysis. Berlin: Springer.Google Scholar
  28. Sjöström, M., Wold, S., & Söderström, B. (1986). PLS discrimination plots. In E. S. Gelsema & L. N. Kanals (Eds.), Pattern recognition in practice (Vol. II). Amsterdam: Elsevier.Google Scholar
  29. Sotelo, A., Sousa, V., & Montalvo, I. (1990). Chemical composition of different fractions of 12 Mexican varieties of rice obtained during milling. Cereal Chemistry, 67(2), 209–212.Google Scholar
  30. Sun, H., & Siebenmorgen, T. J. (1993). Milling characteristics of various rough rice kernel thickness fractions. Cereal Chemistry, 70, 727–733.Google Scholar
  31. Varnamkhasti, M. G., Mobli, H., Jafari, A., Keyhani, A. R., Soltanabadi, M. H., Rafiee, S., & Kheiralipour, K. (2008). Some physical properties of rough rice (Oryza sativa L.) grain. Journal of Cereal Science, 47(3), 496–501.CrossRefGoogle Scholar
  32. Vithu, P., & Moses, J. A. (2016). Machine vision system for food grain quality evaluation: A review. Trends in Food Science & Technology, 56, 13–20.CrossRefGoogle Scholar
  33. Wouters, A., & Baerdemaeker, J. (1988). Effect of moisture content on mechanical properties of rice kernel under quasi-static compressive loading. Journal of Food Engineering, 7, 83–111.CrossRefGoogle Scholar
  34. Zhang D & Lu G (2002). A comparative study of Fourier descriptors for shape representation and retrieval. Proceedings of the 5 th Asian conference of computer vision (ACCV’,02): 646–651.Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • F. Antonucci
    • 1
  • S. Figorilli
    • 1
  • C. Costa
    • 1
  • F. Pallottino
    • 1
  • A. Spanu
    • 2
  • P. Menesatti
    • 1
  1. 1.Centro di ingegneria e trasformazioni agroalimentariConsiglio per la ricerca in agricoltura e l’analisi dell’economia agraria (CREA)RomeItaly
  2. 2.Dipartimento di AgrariaUniversità degli Studi di SassariSassariItaly

Personalised recommendations