با همکاری انجمن علمی گیاهان دارویی ایران

نوع مقاله : مقاله علمی پژوهشی

نویسندگان

1 استاد، مرکز تحقیقات آزمایشگاهی غذا و دارو، سازمان غذا و دارو، وزارت بهداشت، درمان و آموزش پزشکی، تهران، ایران

2 استادیار، اداره آزمایشگاه کنترل غذا و دارو، معاونت غذا و دارو، دانشگاه علوم پزشکی گناباد، گناباد، ایران

3 استادیار، گروه مهندسی برق و کامپیوتر، مجتمع آموزش عالی گناباد

4 دانشجوی دکتری علوم و صنایع غذایی، دانشگاه فردوسی مشهد، مشهد، ایران

چکیده

زعفران یکی از گرانترین ادویه­های جهان محسوب می­شود. زعفران ادویه­ای که بسیار مورد تقلب قرار می­گیرد. توسعه تکنیک­های مبتنی بر ابزار ساده، ارزان قیمت، مناسب و سریع در صنایع غذایی جهت تشخیص تقلّباتی همچون تقلّبات زعفران ضروری است. در پژوهش حاضر، ترکیب پردازش تصویر و روش ماشین بردار پشتیبان (SVM) برای ارزیابی سریع و غیر مخرّب تشخیص زعفران واقعی از زعفران تقلبی به کار رفته است. پس از تهیه تصاویر از توده زعفران خالص و تقلّبی و کلاله­های مجزا، تصاویر وارد مراحل پیش پردازش شدند و در نهایت، ویژگی­های آماری مرتبط با بافت تصاویر و ویژگی­های مورفولوژی شامل 105 ویژگی استخراج شدند. به منظور افزایش سرعت و دقت طبقه­بندی، از روش آنالیز مؤلفه­های اصلی PCA برای کاهش ابعاد ماتریس ویژگی استفاده شد. همچنین طبقه­بندی تصاویر به کمک توابع کرنل مختلف SVM ،به صورت دو کلاس انجام شد. سپس شاخص­های آماری نظیر دقت، صحت، حساسیّت، اختصاصی بودن و سطح زیر منحنی به منظور ارزیابی طبقه­بند محاسبه شدند که مقادیر این شاخص­ها برای طبقه­بندی با کرنل کوبیک SVM برای تشخیص زعفران تقلبی از زعفران واقعی به ترتیب 97، 93، 83، 5/97و 97 درصد بدست آمد. نتایج حاصل از این طبقه­بندی نشان داد که این سیستم به عنوان یک روش هوشمند، سریع، غیرمخرب و دقیق، قابلیت تشخیص زعفران واقعی را از تقلبی  دارد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Application of computer vision on non-destructive detection of the authentic and adulterated saffron

نویسندگان [English]

  • Behrouz akbari-adergani 1
  • morteza mohammadzade moghadam 2
  • mehdi Karimi noghabi 2
  • Mojtaba Mohammadpour 3
  • Mohammad Khalilian-Movahhed 4

1 Professor, Food and Drug Laboratory Research Center, Food and Drug Administration, Ministry of Health and Medical Education, Tehran, Iran

2 Assistant Professor, Food and Drug Control Laboratory Office, Food and Drug Deputy, Gonabad University of Medical Sciences, Gonabad, Iran

3 Assistant Professor, Department of Electrical & Computer Engineering, Faculty of Engineering, University of Gonabad, Gonabad, Iran

4 PhD Student, Department of Food Science and Technology, Ferdowsi University of Mashhad, Mashhad, Iran

چکیده [English]

Saffron is one of the most expensive spices in the world. Saffron is a spice that is widely cheated. The development of techniques based on simple, inexpensive, appropriate and fast tools in the food industry is essential for detecting adulteration such as saffron adulterated. In the present study, the combination of image processing and Support vector machine (SVM) method has been used for fast and non-destructive evaluation of distinguishing authentic saffron from adulterated saffron. After preparing images from pure and counterfeit saffron and separate stigmas, the images entered the pre-processing stages and finally, statistical features related to the texture of the images and morphological features including 105 features were extracted. In order to increase the speed and accuracy of classification, PCA principal component analysis method was used to reduce the properties of the feature matrix. Also, the images were classified into two classes using different SVM kernel functions. Also, the images were classified into two classes using different SVM kernel functions. Then statistical indicators such as accuracy, precision, sensitivity, specificity and AUC were calculated to evaluate the classification. The values of these indices for classification with SVM cubic kernel for authentic saffron were 97, 98, 99, 93 and 97%, and for adulterated saffron, 97, 93, 83, 97.5 and 97% were obtained, respectively. The results of this classification showed that this system, as an intelligent, fast, non-destructive and accurate method, has the ability to distinguish the authentic saffron from adulterated saffron.

کلیدواژه‌ها [English]

  • Saffron
  • fraud
  • Image processing
  • SVM
 
Aghamohamadian-Sharbaf, M., Pourreza, H.R., and Banaee, T. 2016. A novel curvature-based algorithm for automatic grading of retinal blood vessel tortuosity. IEEE Journal of Biomedical and Health Informatics 20: 586-595.
Amirvaresi, A., Nikounezhad, N., Amirahmadi, M., Daraei, B., and Parastar, H. 2021. Comparison of near-infrared (NIR) and mid-infrared (MIR) spectroscopy based on chemometrics for saffron authentication and adulteration detection. Food Chemistry 344: 128647.
Amirvaresi, A., Rashidi, M., Kamyar, M., Amirahmadi, M., Daraei, B., and Parastar, H. 2020. Combining multivariate image analysis with high-performance thin-layer chromatography for development of a reliable tool for saffron authentication and adulteration detection. Journal of Chromatography A 1628: 461461.
Bhooma, V., Nagasathiya, K., Vairamani, M., and Parani, M. 2020. Identification of synthetic dyes magenta III (new fuchsin) and rhodamine B as common adulterants in commercial saffron. Food Chemistry 309: 125793.
Cen, H., Lu, R., Zhu, Q., and Mendoza, F. 2016. Nondestructive detection of chilling injury in cucumber fruit using hyperspectral imaging with feature selection and supervised classification. Postharvest Biology and Technology 111: 352-361.
de Oliveira, E.M., Leme, D.S., Barbosa, B.H.G., Rodarte, M.P., and Pereira, R.G.F.A. 2016. A computer vision system for coffee beans classification based on computational intelligence techniques. Journal of Food Engineering 171: 22-27.
Farag, M.A., Hegazi, N., Dokhalahy, E., and Khattab, A.R. 2020. Chemometrics based GC-MS aroma profiling for revealing freshness, origin and roasting indices in saffron spice and its adulteration. Food Chemistry 331: 127358.
Faucitano, L., Huff, P., Teuscher, F., Gariepy, C., and Wegner, J. 2005. Application of computer image analysis to measure pork marbling characteristics. Meat Science 69: 537-543.
Feizi, J., and Hemmati Kakhki, A. 2006. Identification of colored styles as one of the saffron adulteration with HPLC. Iranian Journal Food Science and Technology Research 2 (2). (In Persian with English Summary).
Hagh-Nazari, S., and Keifi, N. 2006. Saffron and various fraud manners in its production and trades. II International Symposium on Saffron Biology and Technology 739: 411-416.
Heidarbeigi, K., Mohtasebi, S.S., Rafiee, S., Ghasemi-Varnamkhasti, M., Rezaei, K., and Rodriguez-Mendez, M.L. 2015. An electronic tongue design for the detection of adulteration in saffron samples. Iranian Journal of Biosystems Engineering 46: 405-413. (In Persian with English Summary).
Hu, M.H., Dong, Q.L., and Liu, B.L. 2016. Classification and characterization of blueberry mechanical damage with time evolution using reflectance, transmittance and interactance imaging spectroscopy. Computers and Electronics in Agriculture 122: 19-28.
Huang, M., Tang, J., Yang, B., and Zhu, Q. 2016. Classification of maize seeds of different years based on hyperspectral imaging and model updating. Computers and Electronics in Agriculture 122: 139-145.
Javanmardi, N., Bagheri, A., Moshtaghi, N., Sharifi, A., and Hemati Kakhki, A. 2011. Identification of Safflower as a fraud in commercial Saffron using RAPD/SCAR. Journal of Cell and Molecular Research 3: 31-37.
Jolliffe, I. 2011. Principal Component Analysis. International Encyclopedia of Statistical Science. Springer, p. 1094-1096.
Kiani, S., Minaei, S., and Ghasemi-Varnamkhasti, M. 2017. Integration of computer vision and electronic nose as non-destructive systems for saffron adulteration detection. Computers and Electronics in Agriculture 141: 46-53.
Koocheki, A., and Milani, E. 2020. Saffron adulteration. Saffron. Elsevier, p. 321-334.
Kuo, T.Y., Chung, C.L., Chen, S.Y., Lin, H.A., and Kuo, Y.F. 2016. Identifying rice grains using image analysis and sparse-representation-based classification. Computers and Electronics in Agriculture 127: 716-725.
Nasirahmadi, A., Sturm, B., Olsson, A.C., Jeppsson, K.H., Müller, S., Edwards, S., and Hensel, O. 2019. Automatic scoring of lateral and sternal lying posture in grouped pigs using image processing and Support Vector Machine. Computers and Electronics in Agriculture 156: 475-481.
Pantazi, X., Moshou, D., and Tamouridou, A. 2019. Automated leaf disease detection in different crop species through image features analysis and one class classifiers. Computers and Electronics in Agriculture 156: 96-104.
Pourreza, A., Pourreza, H., Abbaspour-Fard, M.H., and Sadrnia, H. 2012. Identification of nine Iranian wheat seed varieties by textural analysis with image processing. Computers and Electronics in Agriculture 83: 102-108.
Rastegaripour, F., and Mohammadi, N. 2018. Investigating factors affecting currency saffron in Iran with emphasis on packaging and branding. Journal of Saffron Research 6: 51-73. (In Persian with English Summary).
Siedliska, A., Baranowski, P., and Mazurek, W. 2014. Classification models of bruise and cultivar detection on the basis of hyperspectral imaging data. Computers and Electronics in Agriculture 106: 66-74.
Taheri-Garavand, A., and Yousefian, M. 2020. Application of computer vision on non-destructive detection of grape syrup adulteration. Innovative Food Technologies 7: 479-495.
Wang, A., Zhang, W., and Wei, X. 2019. A review on weed detection using ground-based machine vision and image processing techniques. Computers and Electronics in Agriculture 158: 226-240.
Xie, C., Yang, C., and He, Y. 2017. Hyperspectral imaging for classification of healthy and gray mold diseased tomato leaves with different infection severities. Computers and Electronics in Agriculture 135: 154-162.