Study of the Impact of the Use of Technical Vision on the Quality Indicators of Omani Halva

The article is devoted to methods and methods of improving the quality of production of Omani desserts (halva) by using a technical vision system to automate quality control with the ability to control the production of this product. It is shown that during the production of Omani halva, problems arise with the stability of the quality indicators of the raw materials used, which affects the quality of the finished halva. Therefore, a system analysis of the automation object - the production line of Omani halva was carried out. The analysis of features of all stages of its production, as well as information processes occurring in them, is given. The characteristic of the main stages of production of Omani halva is presented. A comprehensive analysis of the most important organoleptic quality indicators of Omani halva controlled in the production process is made. The existing methods and tools of these indicators are considered and analyzed. Disadvantages of laboratory organoleptic control are presented. The most informative organoleptic indicators of quality control of raw materials used in the production of Omani halva are selected and justified: size (shape), color and surface condition. These indicators must be monitored during the production of Omani halva. It is shown that currently existing methods for evaluating these quality indicators are subjective and are determined only by experts through laboratory measurements. The existing instrumental methods and means of automatic control in the flow of these indicators are considered and analyzed. The review and analysis of the data obtained in the conducted study showed that it is impossible to use existing methods and tools to automate the control of selected indicators in the flow during the production of Omani halva. The possibility of using technical vision systems to automate the control of selected organoleptic quality indicators of Omani halva is analyzed. The conducted research allowed us to conclude that the use of the technical vision system for these purposes is promising. The composition of a typical technical vision system is presented. The solutions for choosing different types of lenses for solving various tasks are analyzed and the most promising lenses for solving the planned tasks are proposed. One of the most important stages of the technical vision system - image processing-has been studied and analyzed. The most effective algorithm for processing the resulting image was selected. Various image levels are presented and their influence on the quality of the result obtained when controlling bulk raw materials in the flow is considered.

Using the chosen algorithm, experimental studies were conducted to determine the size of nuts, apples, oranges, strawberries, dates, i.e. raw materials used in the production of Omani halva. The prospects of using 3-dimensional image analysis to obtain highly effective information about organoleptic indicators of the quality of food bulk raw materials used in the production of Omani halva are shown.

1. Agoston, M. K. (2004). Computer Graphics and Geometric Modeling. Springer.

2. Ali, S. M. (2013). Gap-Filling Restoration Methods for ETM+ Sensor Images. Iraqi Journal of Science, 54(1),206-214.

3. Antipov, S. T., Kretov, I. T., Ostrikov, A. N. (2009). Mashiny i apparaty pishchevyh proizvodstv [Machines and equipment for food production]. KolosS.

4. Balykhin, M. G., Blagoveshchenskaya, M. M., Blagoveshchenskiy,I. G., Makarovskaya, Z V., & Nazoykin,E.A. (2019). Automation of vacuum freeze-drying products using the combined control method. Izvestiya vysshih uchebnyh zavedenij. Tekhnologiya tekstil’noj promyshlennosti [News of higher educational institutions.Technology of the textile industry], 2(380), 133-137.

5. Balykhin, M. G., Borzov, A. B., & Blagoveshchenskiy, I. G. (2017). The architecture and basic concept of creating an intelligent expert system of food quality control. Pishchevaya promyshlennost’[Food industry], 11, 60 - 63.

6. Balykhin, M. G., Borzov, A. B., & Blagoveshchenskiy, I. G. (2017). Methodological foundations of creating expert systems for monitoring and forecasting the quality of food products using intelligent technologies. Frantera.

7. Benosman, R. (2001). Panoramic vision : Sensors, theory. New York. XXIV.

8. Bityukov, V. K., Khvostov, A. A., & Rebrikov, D. I. (2008). Expert system for determining the color characteristics of bakery products. In Sistemy upravleniya i informacionnye tekhnologii [Management Systems and Information Technologies](pp. 138 – 141).

9. Blagoveshchenskaya, M. M. (2009). Basics of stabilization of the preparation of multicomponent masses. Frantera.

10. Blagoveshchenskiy, I. G., Makarovskaya, Z. V., Blagoveshchenskaya, M. M., Chuvakhin, S. V., & Mitin, V. V. (2019). Using a digital video camera as an intelligent sensor of an automatic control system for the molding of granular food masses. In Intellektual’nye sistemy i tekhnologii v otraslyah pishchevoj promyshlennosti [Intelligent systems and technologies in the food industry branches] (pp. 71-75).

11. Blagoveshchenskaya, M. M., Santon Kunnikhan, M. P. (2017). The structure of dosing control systems using neural networks. In Obshcheuniversitetskaya studencheskaya konferenciya studentov i molodyh uchenyh «Den’ nauki» [University Conference of Students and Young Scientists “Science Day”] (pp. 263 – 267).

12. Fattal, R. (2007). Image upsampling via imposed edges statistics. ACM Transaction on Graphics, 26(3), Article 95. http://doi.acm.org/10.1145/1239451.1239546

13. Fisher, R. A. (2006). The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics.

14. Garcia, L. A., Arguesso, F., Garcia, A. I., & Diaz, M. (1995). Application of neural networks for controlling and predicting quality parameters in beer fermentation. Journal of industrial microbiology, 5, 28 – 35.

15. Gardner J., & Bartlett P. (1998). Electronic Noses: Principles and Applications. Oxford University Press.

16. Gorban, A. N. (2007). Principal Manifolds for Data Visualisation and Dimension Reduction. Springer.

17. Komarinskiy, S. (2008). The Cognitive Visualization System. In Astronomical Data Analysis Software and Systems (ADASS) XVII (pp. 252 – 386).

18. Krylova, L. A., Blagoveshchenskiy, V. G., & Tatarinov, A.V. (2017). Development of intelligent hardware and software systems for monitoring the separation of dispersed food masses based on intelligent technologies. In Razvitie pishchevoj i pererabatyvayushchej promyshlennosti Rossii: kadry i nauka [The Development of the Food and Processing Industry of Russia: Personnel and Science] (pp. 199–201). Publishing complex MGUPP.

19. Legin, A., Rudnitskaya, A., Vlasov, Yu., Di Natale, C., & D’Amico, A. (1999). Sensors and Actuators. West Publishing Company.

20. Lurie I.S. (1989). Tekhnologiya i tekhnologicheskij kontrol’ konditerskogo proizvodstva [Technology and technological control of confectionery production](pp. 243 – 318). Legkaya i pishchevaya promyshlennost’.

21. Newton, D. E. (2007). Food Chemestry. Facts On File.

22. Petrov, A. Yu., Blagoveshchenskaya, M. M., Blagoveshchenskiy, V. G., Ionov, A. V., & Blagoveshchenskiy, I. G. (2019). The main principles in building a computer vision system in the baking industry. In Intellektual’nye sistemy i tekhnologii v otraslyah pishchevoj promyshlennosti [Intelligent systems and technologies in the food industry industries] (pp. 121 – 126).

23. Petryakov, A. N., Blagoveshchenskaya, M. M., Blagoveshchensky, V. G., & Krylova, L. A. (2018). The use of object-oriented programming methods to control the quality indicators of confectionery products. Konditerskoye i khlebopekarnoye proizvodstvo [Confectionery and bakery production],5 – 6 (176), 21-23.

24. Petryakov, A. N., Blagoveshchenskaya, M. M., Blagoveshchenskiy, V. G., Mitin, V. V., & Blagoveshchenskiy, I. G. (2019). Improving the quality of identification and positioning of an object in digital stereo images using depth mapping algorithms. In Intellektual’nye sistemy i tekhnologii v otraslyah pishchevoj promyshlennosti [Intelligent systems and technologies in the food industry industries] (pp. 133 – 138).

25. Savostin, S. D., Blagoveshchenskaya, M. M., & Blagoveshchenskiy, I. G. (2016). Avtomatizaciya kontrolya pokazatelej kachestva muki v processe razmola s ispol’zovaniem intellektual’nyh tekhnologij [Automation of control of flour quality indicators during grinding using intelligent technologies]. Frantera.

26. Semenov, G. V., Krasnova, I. S., Suvorov, O. A., Shuvalova, I. D., & Posokhov, N. D. (2015). Influence of freezing and drying on phytochemical properties of various fruit. Biosciences Biotechnology Research Asia,12(2), 1311-1320.

27. Semenov, G. V., Tikhomirov, A. A., & Krasnova, I. S. (2016). The choice of the parameters of vacuum freeze drying to Thermolabile materials with desired quality level. International Journal of Applied Engineering Research, 11(13), 8056-8061.

28. Storch L.V. (2013). Sovershenstvovanie tekhnologii hleba dlya shkol’nogo pitaniya s primeneniem avtomatizirovannoj sistemy kontrolya cveta izdelij [Improving the technology of bread for school meals using an automated color control system for products] : Abstract. dis. ... cand. tech. Sciences. VGUIT.

29. Sun, D. W. (2008). Modern Techniques for food authentication. Academic Press.

30. Tikhomirov, A. A., & Matison, V. A. (2016). A study on the problem of customer relation ship-oriented design food. Research Journal of Pharmaceutical, Biological and Chemical Sciences, 7(4), 2680-2690.

31. Tikhomirov, A. A., & Matison, V. A. (2016). On the application of consumer evaluation in developing new food products. International Journal of Applied Business and Economic Research, 14(14), 735-746.

32. Wilson, C. I., & Threapleton L. (2003). Application Of Artificial Intelligence For Predicting Beer Flavours From Chemical Analysis. In European Brewery Convention (pp. 18 – 25).