نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشیار گروه مهندسی بیوسیستم، دانشکده کشاورزی، دانشگاه شهید چمران اهواز

2 دانش آموخته کارشناسی ارشد، گروه مهندسی بیوسیستم، دانشکده کشاورزی، دانشگاه شهید چمران اهواز

3 استاد گروه مهندسی برق، دانشکده مهندسی، دانشگاه شهید چمران اهواز

چکیده

در فرآیند تولید شکر، کنترل میزان رشد کریستال‌های شکر در مراحل دانه‌سازی، برای داشتن ذرات شکر با اندازه مورد نیاز و یکسان، ضروری است. امروزه از روش‌های مختلفی به ویژه پایش چشمی توسط اپراتور برای تعیین اندازه ذرات استفاده می‌شود، که روشی زمان‌بر و کم دقت است. هدف از این پژوهش ارائه الگوریتم پردازش تصویر مناسب برای تعیین اندازه کریستال‌های شکر در محلول پخت (مسکوئیت) بود که بتواند ویژگی‌های اندازه و شکل ذرات درون دیگ پخت را ارائه دهد. نمونه-های مسکوئیت از کارخانه تولید شکر شرکت کشت و صنعت نیشکر دعبل خزایی تهیه شدند. پس از آماده‌سازی نمونه‌ها در زیر لام و لامل، با یک دوربین دیجیتال متصل به میکروسکوپ با رزولیشن دو مگاپیکسل تصویربرداری شد. در جعبه ابزار پردازش تصویر نرم‌افزار متلب، ابتدا تبدیل تصویر رنگی به خاکستری، حذف نویزها با عملیات فرسایش و گسترش به کمک فیلترهای مکانی از جمله فیلتر میانه و بهبود کنتراست با تابع تعدیل محلی هیستوگرام انجام شد. برای بخش‌بندی تصویر، سه روش تحدّب، خوشه‌بندی فازی و میکو و ترکیب آنها استفاده شد. در نهایت ضریب تغییرات روش‌های دستی و الگوریتم‌های پردازش تصویر محاسبه و با یکدیگر مقایسه شد و درصد خطای محاسبه میانگین روزنه بدست آمد. در تصویر بخش‌بندی شده دستی، میانگین روزنه ذرات شکر برابر 0/422 میلی‌متر و انحراف معیار 0/157 میلی‌متر با ضریب تغییرات برابر 37/18 درصد بدست آمد. در بخش‌بندی تصویر با روش ترکیبی میکو-تحدّب، میانگین روزنه ذرات شکر برابر 0/382 میلی‌متر و انحراف معیارشان 0/150 میلی‌متر با ضریب تغییرات برابر 39/23 درصد بدست آمد. میانگین خطای اندازه‌گیری میانگین روزنه نسبت به روش دستی برابر با 13/24 درصد و ضریب همبستگی مقادیر میانگین روزنه دو روش 0/88 بود. به دلیل نزدیکی مقادیر ضریب تغییرات، روش بخش‌بندی میکو-تحدّب برای تعیین اندازه کریستال‌های شکر در مسکوئیت با پردازش تصویر مناسب‌تر بود.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Determining the Sugar Crystals Size in Massecuite using Image Processing Algorithms

نویسندگان [English]

  • Hassan Masoudi 1
  • Seyed Mahmood Asadi 2
  • Gholamreza Akbarizadeh 3

1 Associate professor, Department of Biosystems Engineering, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Khuzestan, Iran

2 Graduated M.Sc. student, Department of Biosystems Engineering, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Khuzestan, Iran

3 Professor, Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Khuzestan, Iran

چکیده [English]

Introduction: In sugar factories, control of sugar crystals growth in the granulation stages is very important to produce sugar grains with a special and required size. Machine vision systems can determine the size of sugar crystals. The main challenge of image processing systems is the lack of capable algorithms to separate contact and overlap crystals accurately. So far, various algorithms have been developed to detect crystals and remove their overlapping. However, these methods have not been able to fully detect and separate the overlap of crystals. The purpose of this study was to provide an appropriate image processing algorithm for determining the size of crystals in sugar baking solution (massecuite), which gives us the characteristics of size and shape for the particles in the baking pot instantly to evaluate and improve the quality of the final product.

Materials and Methods: The massecuite samples were provided from Debal Khozaei Sugarcane Agro-industrial Company, Ahvaz, Iran. After preparation of the sugar crystals samples under lam and lamer (microscope slides), a digital camera with two Megapixel resolution, attached to a ZS9 Olympus microscope, was used for image capturing. Then, using MATLAB image processing toolbox, the color image (RGB) transferred to grey scale. A mixture of structural operations such as erosion and expansion with spatial filters including median filter were used to remove the image noises. The function of histogram local adjustment was used to improve image contrast. Three methods of segmentation including convexity, fuzzy clustering, and multiplicative intrinsic component optimization (MICO), along with their combination were used to segment the image of massecuite crystals. A reference image was used to determine accuracy of the image processing algorithms. To do this, the massecuite crystals image was manually segmented by Image J software. All segmentation algorithms were applied on the reference image, and seven geometrical parameters, including the mean aperture (MA), coefficient of variation (CV), and standard deviation (SD) were calculated for all the sugar particles in the image. Finally, the percent of MA measurement error was calculated for each sugar crystal to find the best algorithm.

Results and Discussion: In manual segmentation, the number of sugar crystals in the selected image was 26. In the manually segmented image, the average of MA, SD and CV for sugar grains in the image were 0.422 mm, 0.157 mm and 37.18% respectively. The relatively large CV of the calculated geometrical parameters indicated the non-uniformity of the sugar particles size inside the massecuite. The convexity method was able to perform well in some areas of the image, and in some other areas, it could not detect the contact between the crystals. The value of the SD and CV of all the geometric parameters determined by the convexity method were greater than the reference values determined by the manual segmentation. This indicates the weaker performance of this method in determining the sugar crystals size compared to the manual method. The values of SD and CV of all geometric parameters determined by the combined fuzzy-convexity method were greater than the reference values, but lower than the values of the convexity method alone. So, the combination of the fuzzy clustering method with the convexity method improved the segmentation performance of crystal images. The SD and CV values of all geometric parameters determined by the combined MICO-convexity method were greater than the reference values, but lower than the values of convexity and fuzzy-convexity methods. This point shows the better performance of the combined MICO-convexity method in segmenting the images of sugar crystals compared to the other two methods. The average of MA, SD and CV for sugar crystals in the image were 0.382 mm, 0.150 mm and 39.23% respectively and had no significant difference with the reference method values in 5% probability level. The mean error of MA determined by the combined MICO-convexity algorithm was 13.24% and Pearson correlation factor was 0.88. As a result, the combined MICO-convexity method was proposed to determine the size of sugar crystals in massecuite.

Conclusion: After applying different algorithms on the selected image of sugar crystals in massecuite, it was found that the combined MICO-convexity method can separate sugar crystals well. Also, the CV obtained for this image segmentation algorithm was not much different from the CV of the manual reference method, so this algorithm can be used in the image processing system of the massecuite crystals.

کلیدواژه‌ها [English]

  • Massecuite
  • Digital microscope
  • Image processing
  • Convexity method
  • Fuzzy clustering method
  • MICO method
  1. Argaw, G.A., Alport, M.J., and Malinga, S.B. 2006. Automatic measurement of crystal size distribution using image processing. Proceedings of the South African Sugar Technologists' Association, 80: 399-411.
  2. Argaw, G.A. 2007. Sugar Crystal Size Characterization Using Digital Image Processing. Ph.D. thesis, School of Physics, University of KwaZulu-Natal, Durban, South Africa.
  3. Asadi, S.M. 2017. Presentation of a Machine Vision Algorithm for Size Determination of White Sugar and Massecuite Crystals. M.Sc. thesis, Department of Biosystems Engineering, Shahid Chamran University of Ahvaz, Iran. (in Persian with English abstract)
  4. Cardona, M. 2016. Sugar crystals characterization for quality control inspection using digital image processing. IEEE 36th Central American and Panama Convention (CONCAPAN XXXVI), San Jose, Costa Rica, pp. 1-6.
  5. Chayatummagoon, S. and Chongstitvatana, P. 2021. Image classification of sugar crystal with deep learning. 13th International Conference on Knowledge and Smart Technology (KST), Bangsaen, Chonburi, Thailand, pp. 118-122.
  6. Faria, N., Pons, M.N., De Azevedo, S.F., Rocha, F.A., and Vivier, H. 2003. Quantification of the morphology of sucrose crystals by image analysis. Powder Technology, 133: 54-67.
  7. Hayali, Z., and Akbarizadeh, G. 2022. Transfer Learning on Semantic Segmentation for Sugar Crystal Analysis. International Conference on Machine Vision and Image Processing (MVIP), Ahvaz, Iran, pp. 1-6.
  8. Klute, U. 2007. Microwave measuring technology for the sugar industry. Proceedings of the International Society of Sugar Cane Technologists, 26.
  9. Kohansal Makvandy, P., Rahnama, M., Memar Dastjerdy, R., and Shafeinia, A. 2019. Evaluation of some effective parameters in design of horizontal dilute phase pneumatic sugar conveyors. Journal of Agricultural Engineering Soil Science and Agricultural Mechanization, (Scientific Journal of Agriculture), 42(2): 21-36. (in Persian with English abstract).
  10. Larsen, A., and Rawlings, J.B. 2009. Assessing the reliability of particle number density measurements obtained by image analysis. Particle and Particle Systems Characterization, 25, 420-433.
  11. Liao, C.W., Yu, J.H., and Tarng, Y.S. 2010. On-line full scan inspection of particle size and shape using digital image processing. Particuology, 8: 286-292.
  12. Li, C., Gore, J.C., and Davatzikos, C. 2013. Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation. Magnetic Resonance Imaging, 32(7): 913-923.
  13. Masoudi, H., Asadi, S.M., and Akbarizadeh, G. 2020. Development and Evaluation of an Image Processing Algorithm for Gradation of White Sugar Crystals. Innovative Food Technologies, 8(1): 97-110. (in Persian with English abstract).
  14. Meng, Y., Yu, Sh., Zhang, J., Qin, J., Dong, Zh., Lu, G., Pang, H. 2019. Hybrid modeling based on mechanistic and data-driven approaches for cane sugar crystallization. Journal of Food Engineering, 257: 44-55.
  15. Mhlongo, A.Z. and Alport, M.J. 2002. Application of artificial neural network techniques for measuring grain sizes during sugar crystallization. Proceedings for Congress of the South African Sugar Technologists Association, 76: 460-468.
  16. Miller, K.F., and Beath, A.C. 2000. The measurement of raw sugar crystal size by sieving and laser diffraction. Proceedings of the Australian Society of Sugar Cane Technology, 22: 393-398.
  17. Olofsson, B.I., and Nilsson, H.I. 1992. Particle size measurement system by laser light diffraction. In Proceedings of the Sugar Processing Research Conference, 27-29 September, New Orleans, Louisiana, USA.
  18. Pan, Z.K., Zhu, M.R., and Zhang, Z.S. 2010a. Design of image acquisition system for sucrose crystallization based on ARM9. Application of Computer System, 19: 15-18.
  19. Pan, Z.K., Zhu, M.R., and Zhang, Z.S. 2010b. The research of image acquisition and control system based on crystallization process of sucrose. Manufacturing Automation, 32: 29-32.
  20. Patricio, M.A., and Maravall, D. 2007. A novel generalization of the gray-scale histogram and its application to the automated visual measurement and inspection of wooden Pallets. Image and Vision Computing, 25: 805-816.
  21. Scott, D.M. 2003, Characterizing particle characterization. Particle and Particle Systems Characterization, 20: 305-310.
  22. Theisen, K.H., and Diringer, T. 2000. Microwave concentration measurement for process control in the sugar industry. Proceedings of the Sugar Industry Technologists, 60: 79-92.
  23. Wang, D., and Fan, L.S. 2013. Particle characterization and behavior relevant to fluidized bed combustion and gasification systems. Editor(s): Fabrizio Scala. In Woodhead Publishing Series in Energy, Fluidized Bed Technologies for Near-Zero Emission Combustion and Gasification, Woodhead Publishing, Pages 42-76.
  24. Wang, L.M., Zhu, M.R., and Fan, C.L. 2009. Application of image recognition in sugar crystal size measurement. Computer Simulation, 26: 294-297.
  25. Wu, X., Meng, Y., Zhang, J., Wei, J., Zhai, X. 2023. Amodal segmentation of cane sugar crystal via deep neural networks. Journal of Food Engineering, 348(6): 111435.

 

  1. Zhang, Z.S., Zhu, M.R., and Pan, Z.K. 2010. A method to identify sucrose-crystallization particle based on image. Computer System and Applications, 19: 95-99.
  2. Zhang, B., Abbas, A., and Romagnoli, J.A. 2011. Multi-resolution fuzzy clustering approach for image-based particle characterization for particle systems. Chemometrics and Intelligent Laboratory Systems, 107(1): 155-164.
  3. Zhang, J., Meng, Y., Wu, J., Qin, J., Wang, H., Yao, T., Yu, 2020. Monitoring sugar crystallization with deep neural networks. Journal of Food Engineering, 280: 109965.
  4. Zheng, Y., Wang, X., and Wu, Zh. 2022. Machine Learning Modeling and Predictive Control of the Batch Crystallization Process. Industrial & Engineering Chemistry Resear