Control and Optimize Black Tea Fermentation Using Computer Vision and Optimal Control Algorithm
Black tea is a completely fermented tea. Fermentation is a very important stage in the process of producing black tea because the characteristic color of black tea depends entirely on the factors in this process, such as: humidity, temperature, and fermentation time. To control color variation during fermentation, computer vision is used to detect the color change of black tea in RGB, HSV or CIE LAB color systems. In order to get the fermented tea products of the standard, it is necessary to calculate and adjust exactly the factors affecting the quality of the fermentation process. In fact, the quality of black tea is always correlated with color. The parameters of color characteristics and sensory characteristics of black tea are used to put into the optimal control system for fermentation of black tea, ensuring that the output quality reaches the highest index. This article uses extract features of color in the CIE LAB color system combined with the predictability of RF nonlinear models to analyze the relationship between image information and quality indicators to determine control parameters for the system. Using this method will make the process of monitor and controlling black tea fermentation become simpler and both labor to monitor and the accuracy of the process achieved be higher results than using manual methods.
KeywordsBlack tea fermentation CIE lab Random forests (RF) Computer vision
- 1.Thi Luu, N., Hung, L., Thành, N.T.M.: Textbook of processing black semi-finished black tea. Ministry of Agric High technology of tea production - coffee - coffee - cashew nuts Nha Trang UniversityGoogle Scholar
- 2.Dong, C., Liang, G., Hu, B., Yuan, H., Jiang, Y., Zhu, H., Qi, J.: Prediction of Congou black tea fermentation quality indices from color features using non-linear regression methods. Sci. Rep. (2018)Google Scholar
- 5.Wu, X., Yang, J., Wang, S.: Tea category identification based on optimal wavelet entropy and weighted k-Nearest Neighbors algorithm. Multimed. Tools Appl. 1–15 (2016)Google Scholar
- 6.Xuan Quynh, N.: Research project to build the optimal automation system for processing and preserving agricultural products technology. Ministry of Science and Technology (2015)Google Scholar
- 10.Pitra, Z., Bajer, L., Holeňa, M.: Comparing SVM, Gaussian process and random forest surrogate models for the CMA-ES. In: ITAT 2015: Information Technologies-Applications and Theory, pp. 186–193. CreateSpace Independent Publishing Platform, North Charleston (2015)Google Scholar