با همکاری انجمن علمی گیاهان دارویی ایران

نوع مقاله : مقاله علمی پژوهشی

نویسندگان

1 دانشجوی دکتری، مهندسی علوم و صنایع غذایی، گروه علوم و صنایع غذایی، دانشکده کشاورزی، دانشگاه فردوسی مشهد

2 استادیار، گروه علوم و صنایع غذایی، دانشکده کشاورزی، دانشگاه فردوسی مشهد

3 دانشیار، گروه مکانیک بیوسیستم، دانشکده کشاورزی، دانشگاه فردوسی مشهد

4 استاد، گروه کامپیوتر، دانشکده مهندسی، دانشگاه فردوسی مشهد

چکیده

طبقه­بندی زعفران به عنوان گران­ترین ادویه از اهمیت بالایی برای مشتریان و تجار برخوردار است. به طور کلی، در حال حاضر دو روش برای درجه­بندی زعفران استفاده می­شود. روش اول براساس تجربیات فرد خبره و با مشاهده نمونه­ها انجام می­شود. روش دوم تخریبی بوده و با استفاده از متدهای آزمایشگاهی انجام می­گیرد. طبق نظر متخصصان، استفاده از تکنیک­های یادگیری ماشین برای طبقه­بندی زعفران به دلیل داشتن ماهیت غیر مخرب و خصوصیات بهنگام، یک هدف است. این روش همچنین می­تواند باعث افزایش دقت فرآیند درجه­بندی در مقیاس صنعتی شود. در این مقاله، یک روش مبتنی بر ماشین بینایی ارائه شده است. با توجه به عدم تحقیقات مستند در مورد این موضوع، جستجوی مشروح جامع در این کار ارائه می­شود. تقریباً تمام ویژگی­های رنگ استخراج و در تعداد زیادی از طبقه­بندی کننده­ها استفاده شد. افراد خبره در ایران زعفران را بر اساس خصوصیات ظاهری به سه طبقه اصلی یعنی پوشال، نگین و سرگل طبقه­بندی می­کنند. در این مقاله، یک بانک اطلاعاتی متشکل از 440 تصویر از زعفران برای سه کلاس مختلف با استفاده از دوربین تلفن همراه جمع­آوری شد. پس از اعمال تعدادی از مراحل پیش پردازش مانند حذف پس زمینه، بریدن و حذف مناطق ناخواسته تصاویر و غیره ، 21 ویژگی رنگی با استفاده از روش های مختلف تحلیل تصویر استخراج شد. برای طبقه­بندی از 22 طبقه­بندیگر استفاده شدند. مقایسه نتایج طبقه­بندی کننده­های مختلف نشان داد که Linear Discriminant ، Linear SVM، Bagged Trees و RUSBoost Trees می توانند در هنگام استفاده از ویژگی­های رنگی، درجه­بندی دقیق­تری را نسبت به سایر طبقه­بندی کننده­ها ایجاد کنند. به طور خاص، دراین کار، میانگین دقت 23/82 درصد با استفاده از طبقه­بندی­کننده خطی SVM بدست آمد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Classification of Saffron Using Color Features Extracted from the Image

نویسندگان [English]

  • Morteza Mohamadzadeh moghadam 1
  • Masoud Taghizadeh 2
  • Hassan Sadrnia 3
  • Hamid reza Pourreza 4

1 Ph.D Student of Food Science and Technology, Department of Food Science and Technology, Faculty of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran

2 Assistant Professor, Department of Food Science and Technology, Faculty of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran

3 Associate Professor, Biosystems Engineering. Faculty of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran

4 Department of Computer Engineering. Ferdowsi University of Mashhad IRAN

چکیده [English]

The classification of saffron as the most expensive spice is of great importance for customers and traders. In general, two methods are currently used to classify saffron. The first method is based on the experiences of an expert and by observing the samples. The second method is destructive and is performed using laboratory methods. According to experts, the use of machine learning techniques to classify saffron is a goal due to its non-destructive nature and timely characteristics. This method can also increase the accuracy of the industrial scale grading process. In this paper, a vision machine method is presented. Due to lack of documented research on this subject, a comprehensive literature search is presented in this work. Almost all color characteristics were extracted and used in a large number of classifiers. Experts in Iran classify saffron into three main categories based on their appearance: Pushal, Negin and Sargol. In this paper, a database consisting of 440 images from saffron for the three different classes was collected using a mobile phone camera. After applying some preprocessing steps, such as background removal, cropping etc., 21 color features were extracted using different image analysis methods. Twenty-two classifiers were employed for classification. Comparing results of different classifiers showed that the Linear Discriminant, Linear SVM, Bagged Trees and RUSBoost Trees can produce more accurate grading compared to other classifiers when using color features. In particular, mean classification accuracy of 82.23% was achieved in this work using Linear a SVM classifier.

کلیدواژه‌ها [English]

  • Classification
  • saffron
  • Image processing
Atefi, M., Akbari Oghaz, A., and Mehri, A. 2013. Drying effects on chemical and sensorial characteristics of saffron. Iranian Journal of Nutrition Sciences and Food Technology 8 (3): 201-208. (In Presian with English Summary).
Azarabadi, N., and Özdemir, F. 2018. Determination of crocin content and volatile components in different qualities of Iranian saffron. GIDA/The Journal of FOOD 43 (3).
Azizi, Z., Moradi, S.H., Moradi S.M., Rafat, S.A., and Shodja, J. 2016. Genetic classification of Azari and North ecotype Buffalo population using SVM method. Iranian Journal of Animal Science 47 (2): 279-290.
Bonyadi, M.H.J., Yazdani, S., and Saadat, S. 2014. The ocular hypotensive effect of saffron extract in primary open angle glaucoma: a pilot study. BMC Complementary and Alternative Medicine 14 (1): 399.
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.
Donis-González, I.R., and Guyer, D.E. 2016. Classification of processing asparagus sections using color images. Computers and Electronics in Agriculture 127: 236-241.
Dutta, R., Dutta, R., Smit, D., Rawnsley, R., Bishop-Hurley, G., Hills, J., Timms, G., and Henry, D. 2015. Dynamic cattle behavioural classification using supervised ensemble classifiers. Computers and Electronics in Agriculture 111: 18-28.
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 (3): 537-543.
Fernández, J.A. 2004. Biology, biotechnology and biomedicine of saffron. Recent Research Development and Plant Science 2: 127-159.
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.
Kafi, M., Koocheki, A., and Rashed, M. 2006. Saffron (Crocus sativus): Production and Processing. Science Publishers, Enfield, NH, USA, 1-241.
Kamiński, B., Jakubczyk, M., and Szufel, P. 2018. A framework for sensitivity analysis of decision trees. Central European Journal of Operations Research 26 (1): 135-159.
Kiani, S., and Minaei, S. 2016. Potential application of machine vision technology to saffron (Crocus sativus L.) quality characterization. Food Chemistry 212: 392-394.
Kiani, S., Minaei, S., and Ghasemi-Varnamkhasti, M. 2018. Instrumental approaches and innovative systems for saffron quality assessment. Journal of Food Engineering 216: 1-10.
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.
Martínez, A.M., and Kak, A.C. 2001. Pca versus lda. IEEE Transactions on Pattern Analysis and Machine Intelligence (2): 228-233.
Masi, E., Taiti, C., Heimler, D., Vignolini, P., Romani, A., Mancuso, S. 2016. PTR-TOF-MS and HPLC analysis in the characterization of saffron (Crocus sativus L.) from Italy and Iran. Food Chemistry 192: 75-81.
Minaei, S., Kiani, S., Ayyari, M., and Ghasemi-Varnamkhasti, M. 2017. A portable computer-vision-based expert system for saffron color quality characterization. Journal of Applied Research on Medicinal and Aromatic Plants 7: 124-130.
Mohammadzadeh, A., Golzarian, M., and Abbaspour, F.M. 2016. Classification of pomegranate arils from image features using linear discriminant analysis. Iranian Food Science and Technology Research Journal 12 (1): 182-192. (In Presian with English Summary).
Muhammad, G. 2015. Date fruits classification using texture descriptors and shape-size features. Engineering Applications of Artificial Intelligence 37: 361-367.
Nasirahmadi, A., Sturm, B., Olsson, AC., Jeppsson, KH., Müller, S., Edwards, and S., 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.
Nouri-Ahmadabadi, H., Omid, M., Mohtasebi, S.S., and Firouz, M.S. 2017. Design, development and evaluation of an online grading system for peeled pistachios equipped with machine vision technology and support vector machine. Information Processing in Agriculture 4 (4): 333-341.
Omid, M., Firouz, M.S., Nouri-Ahmadabadi, H., and Mohtasebi, S.S. 2017. Classification of peeled pistachio kernels using computer vision and color features. Engineering in Agriculture, Environment and Food 10 (4): 259-265.
Paulus, I., and Schrevens, E. 1999. Shape characterization of new apple cultivars by Fourier expansion of digitized images. Journal of Agricultural Engineering Research 72 (2): 113-118.
Peter, K.V. 2012. Handbook of Herbs and Spices. Elsevier, 1-640.
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.
Riveiro-Valiño, J., Álvarez-López, C., and Marey-Pérez, M.F. 2009. The use of discriminant analysis to validate a methodology for classifying farms based on a combinatorial algorithm. Computers and Electronics in Agriculture 66 (2): 113-120.
Shahdadi, H., Barati, F., Bahador, R.S., and Eteghadi, A. 2016. Clinical applications of saffron (Crocus sativus) and its constituents: A literature review. Der Pharmacia Lettre 8 (19): 205-209.
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.
Sun, D.W. 2016. Computer Vision Technology for Food Quality Evaluation. Academic Press, 1-583.
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.
Zhang, M., Lee, D.J., Lillywhite, K., and Tippetts, B. 2017. Automatic quality and moisture evaluations using Evolution Constructed Features. Computers and Electronics in Agriculture 135: 321-327.
Zheng, H., and Lu, H. 2012. A least-squares support vector machine (LS-SVM) based on fractal analysis and CIELab parameters for the detection of browning degree on mango (Mangifera indica L.). Computers and Electronics in Agriculture 83: 47-51.