Computer vision techniques for modelling the roasting process of coffee (Coffea arabica L.) var. Castillo

Ivorra E., Sarria-González J.C., Girón-Hernández J. (2020): Computer vision techniques for modelling the roasting process of coffee (Coffea arabica L.) var. Castillo. Czech J. Food Sci., 38: 388–396.

download PDF

Artificial vision has wide-ranging applications in the food sector; it is easy to use, relatively low cost and allows to conduct rapid non-destructive analyses. The aim of this study was to use artificial vision techniques to control and model the coffee roasting process. Samples of Castillo variety coffee were used to construct the roasting curve, with captured images at different times. Physico-chemical determinations, such as colour, titratable acidity, pH, humidity and chlorogenic acids, and caffeine content, were investigated on the coffee beans. Data were processed by (i) Principal component analysis (PCA) to observe the aggrupation depending on the roasting time, and (ii) partial least squares (PLS) regression to correlate the values of the analytical determinations with the image information. The results allowed to construct robust regression models, where the colour coordinates (L*, a*), pH and titratable acidity presented excellent values in prediction (R2Pred 0.95, 0.91, 0.94 and 0.92). The proposed algorithms were capable to correlate the chemical composition of the beans at each roasting time with changes in the images, showing promising results in the modelling of the coffee roasting process.

Aghbashlo M., Hosseinpour S., Ghasemi-Varnamkhasti, M. (2014): Computer vision technology for real-time food quality assurance during drying process. Trends in Food Science & Technology, 39: 76–84.
Alessandrini L., Romani S., Pinnavaia G., Dalla Rosa M. (2008): Near infrared spectroscopy: An analytical tool to predict coffee roasting degree. Analytica Chimica Acta, 625: 95–102.
Barjolle D., Quiñones-Ruiz X., Bagal M., Comoé H. (2017): The role of the state for geographical indications of coffee: Case studies from Colombia and Kenya. World Development, 98: 105–119.
Beucher S., Meyer F. (1993): The morphological approach to segmentation: The watershed transformation. In: Mathematical Morphology in Image Processing, 34: 433-481
Budryn G., Nebesny E., Podsddek A., Ôyrelewicz D., Materska M., Stefan J., Bogdan J. (2009): Effect of different extraction methods on the recovery of chlorogenic acids, caffeine and Maillard reaction products in coffee beans. European Food Research and Technology, 228: 913–922.
De Luca S., De Filippis M., Bucci R., Magrì A.D., Magrì A.L., Marini F. (2016): Characterization of the effects of different roasting conditions on coffee samples of different geographical origins by HPLC-DAD, NIR and chemometrics. Microchemical Journal, 129: 348–361.
Fabbri A., Cevoli C., Alessandrini L., Romani S. (2011): Numerical modeling of heat and mass transfer during coffee roasting process. Journal of Food Engineering, 105: 264–269.
Fadai N.T., Melrose J., Please C.P., Schulman A., Van Gorder, R.A. (2017): An heat and mass transfer study of coffee bean roasting. International Journal of Heat and Mass Transfer, 104: 787–799.
Gabriel-Guzmán M., Rivera V.M., Cocotle-Ronzón Y., García-Díaz, S., Hernández-Martínez E. (2017): Fractality in coffee bean surface for roasting process. Chaos, Solitons and Fractals, 99: 79–84.
Garg S.K. (2016): Green Coffee Bean. In: Nutraceuticals. Academic Press: 653–667
Ginz M., Balzer,H.H., Bradbury,A.G.W., Maier H.G. (2000): Formation of aliphatic acids by carbohydrate degradation during roasting of coffee. European Food Research and Technology, 211: 404–410.
Haralick R., Shanmugam K., Dinstein I. (1973): Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3: 610–621.
Hernández J. A., Heyd B., Trystram G. (2008): Prediction of brightness and surface area kinetics during coffee roastin. Journal of Food Engineering, 89: 156–163.
Mazzafera P. (1999): Chemical composition of defective coffee beans. Food Chemistry, 64: 547–554.
Mery D., Pedreschi F., Soto A. (2013): Automated design of a computer vision system for visual food quality evaluation. Food and Bioprocess Technology, 6: 2093–2108.
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9: 62–66.
Piccardi, M. (2004). Background subtraction techniques: A review. IEE Xplore, 4: 3099–3104.
Rodríguez Y.F.B., Guzmán N.G., Hernández J.G. (2020): Effect of the postharvest processing method on the biochemical composition and sensory analysis of arabica coffee. Engenharia Agrícola, 40: 177–183.
SCA (2018): The Washed Arabica Green Coffee Defect Guide. 3rd Ed. Specialty Coffee Association. Chelmsford, United Kingdom: 1–36.
Santos J.R., Lopo M., Rangel A.O., Lopes J.A. (2016a): Exploiting near infrared spectroscopy as an analytical tool for on-line monitoring of acidity during coffee roasting. Food Control, 60: 408–415.
Santos J.R., Viegas O., Páscoa R., Ferreira I., Rangel A., Lopes, J.A. (2016b): In-line monitoring of the coffee roasting process with near infrared spectroscopy: Measurement of sucrose and colour. Food Chemistry, 208: 103–110.
Sarria-González J.C., Ivorra-Martínez E., Girón-Hernández J. (2019): Control of the coffee roasting stage using artificial vision techniques. Coffee Science, 14: 33–37.
Vala H. J., Astha B. (2013): An review on Otsu image segmentation algorithm. International Journal of Advanced Research in Computer Engineering & Technology, 2: 387–389.
Wang N., Lim L.T. (2012): Fourier transform infrared and physicochemical analyses of roasted coffee. Journal of Agricultural Food Chemestry, 60: 5446–5453.
Wang Y., Ho C.T. (2013): Effects of naturally occurring phenolic compounds in coffee on the formation of maillard aromas. In: Ho Ch.T., Mussinan C., Shahidi F., Contis E.T. (eds): Nutrition, Functional and Sensory Properties of Foods, RSC publishing, UK: 98–110.
Wang X., Lim L. T. (2015): Physicochemical characteristics of roasted coffee. In: Preedy V.R. (ed.) Coffee in health and disease prevention. Elsevier Academic Press, USA: 247–1254.
Wei F., Furihata K., Koda M., Hu F., Miyakawa T., Tanokura M. (2012): Roasting process of coffee beans as studied by nuclear magnetic resonance: Time course of changes in composition. Journal of Agricultural and Food Chemistry, 60: 1005–1012.
Wieland F., Gloess A., Keller M., Wetzel A., Schenker S., Yeretzian C. (2012): Online monitoring of coffee roasting by proton transfer reaction time-of-flight mass spectrometry (PTR-ToF-MS): Towards a real-time process control for a consistent roast profile. Analytical and Bioanalytical Chemistry, 402: 2531–2543.
Yun Y.H., Li H.D., Deng,B.C., Cao D.S. (2019). An overview of variable selection methods in multivariate analysis of near-infrared spectra. TrAC Trends in Analytical Chemistry, 113: 102–115.
download PDF

© 2021 Czech Academy of Agricultural Sciences | Prohlášení o přístupnosti