تخمین محتوای نیترات گوجه‌فرنگی با استفاده از ویژگی‌های تصویر

نویسندگان
سید مهدی نصیری
محمد امین نعمت اللهی
عبدالعباس جعفری
پیمان سلمرودی
دانشگاه شیرازبخش مهندسی بیوسیستم
10.22034/FSCT.21.152.1
چکیده
کاربرد ناصحیح کودهای شیمیایی در تولید محصولات کشاورزی بروز بیماری برای مصرف‌کنندگان را ممکن می‌سازد. در این مطالعه تخمین مقدار نیترات تجمع ‌یافته در میوه گوجه‌فرنگی به کمک پردازش تصویر بررسی شد. این پژوهش در قالب طرح کاملا تصادفی با چهار تیمار نیتروژن در سطوح 1200،800،400 و 1600 کیلوگرم بر هکتار انجام شد. از هر تیمار 50 نمونه به طور تصادفی برای تهیه تصاویر و ایجاد مدل تخمین انتخاب شد. نمونه‌ها با ضخامت یکسان برش زده شدند، عکس‌برداری صورت گرفت و سپس نیترات نمونه‌ها به روش آزمایشگاهی اندازه‌گیری شد. مولفه­ های رنگی R، G و B مرتبط با سطح و محتوای داخلی نمونه‌ها و همچنین ویژگی‌های غیر­رنگی از جمله مساحت پیکسل­های سفید ورقه‌ها ، مساحت کل ورقه‌ها و نسبت مساحت پیکسل­های سفید به مساحت کل استخراج شدند. نتایج نشان داد متناسب با سطوح نیتروژن اعمال شده، مقدار نیترات نمونه­ها به ترتیب 6/1، 7/2، 8/2 و 3/3 درصد اندازه­گیری شد که این افزایش معنادار بود (P<0.05). افزون بر آن، مشخص شد محتوای رنگی ورقه‌ها، مساحت پیکسل­های سفید ورقه‌ها و نسبت مساحت پیکسل­های سفید به مساحت کل همبستگی بالایی با محتوای نیترات نمونه‌ها داشت. برای پیش‌بینی میزان نیترات، مدل رگرسیون چندگانه و شبکه عصبی چند لایه پرسپترون بکاربرده شد. روش بهترین زیر مجموعه رگرسیون برای انتخاب مناسب­ترین مدل رگرسیون بکاربرده شد. برای انتخاب بهترین مدل شبکه عصبی، معماری‌ها و توابع انتقال مختلف به کار برده شد و بر اساس نتایج شبکه‌ با ساختار 1-15-3 با کمترین مقدار ریشه میانگین مربعات خطا به عنوان بهترین مدل انتخاب شد. برای واسنجی بهترین مدل‌ رگرسیون و شبکه عصبی از 60 نمونه جدید استفاده شد. ساختار معرفی شده توانست با درصد میانگین خطای نسبی 5/3 درصد در مقایسه با مدل رگرسیون با مقدار 2/5 درصد مقدار محتوای نیترات را تخمین بزند.
کلیدواژه‌ها
پردازش تصویر
رگرسیون
شبکه عصبی مصنوعی
گوجه‌فرنگی
نیترات

موضوعات

عنوان مقاله English

Estimation of nitrate content in tomato using image features

نویسندگان English

Seyed Mehdi Nassiri
Mohammad Amin Nematollahi
Abdolabbas Jafari
Peyman Salamrudi
Department of Biosystems EngineeringShiraz University
چکیده English

The improper use of chemical fertilizers in crop production can result in unsafe food sources for consumers. This research focuses on estimating the accumulation of nitrate in tomatoes by analyzing images of tomato tissues. The experiments were conducted using a completely randomized design with four nitrogen levels: 400, 800, 1200, and 1600 kg.ha-1. Fifty samples were randomly selected from each treatment to create images for feature processing and develop a prediction model. The samples were sliced to a consistent thickness, and their images were prepared. The nitrate contents of the same samples were then measured in the laboratory. Color features, including R, G, and B color components, as well as non-color features such as white pixel area (WPA), total slice surface area (TSA), and the ratio of white pixel area to total slice surface area (WPA/TSA), were extracted from the images. The results showed that the nitrate content of the samples increased significantly (P<0.05) in response to the applied nitrogen fertilizer, with measurements of 1.6%, 2.7%, 2.8%, and 3.3%, respectively. Moreover, a strong correlation was found between the color components, WPA, TSA, WPA/TSA, and nitrate accumulation in the samples. Multiple regression and multilayer perceptron neural network (MLP) models were employed to predict the nitrate content. The best subset method was used to build an appropriate regression model. Various topologies and transform functions were applied to identify the best MLP model. The results indicated that an MLP model with a 3-15-1 topology and the lowest mean relative percentage error (MRPE) was the most accurate neural network model. The final regression and neural network models were validated using 60 intact samples. The neural network model achieved a MRPE of approximately 3.5%, demonstrating its precise estimation of nitrate contents compared to the regression model with an MRPE of around 5.2%.

کلیدواژه‌ها English

Image processing
Neural Network
Nitrate
Regression
Tomato
[1] Lugasi, A., Bíró, L., Hóvárie, J., Sági, K. V., Brandt, S., & Barna, E. (2003). Lycopene content of foods and lycopene intake in two groups of the Hungarian population. Nutrition Research, 23(8), 1035-1044.
[2] Anonymous. (2020). FAO statistics: Crop product. Available at: https://www.fao.org/faostat/en/#data/QV.
[3] Manrique, L. A. (1993). Greenhouse crops: A review. Journal of Plant Nutrition, 16(12), 2411-2477.
[4] Malakooti, M. J., & Tabatabaei, S.J. (1998). Application of organic and chemical fertilizers for potato production and control nitrate concentration of potatoes’ tubers in Iran. Nashre Amozesh Keshavarzi Publication. Karaj, Iran. (in Farsi)
[5] Mazaheri Tehrani, M., Mortazavi, S. A., Ziaolhagh, H. R., & Ghandi, A. (2007). Tomato production and processing. Volume 1. Marzedanesh Publication, Tehran. Iran. (in Farsi)
[6] Ahmadi, H., Delshad, M., & Babalar, M. (2014). Effect of K and N concentration in nutrient solution on growth and quality of tomato transplants. Iranian Journal of Horticultural Sciences, 2(45), 197-205. (in Farsi)
[7] Matthew, N. B., Augustine, A. U., Shaibu, S. E., Akomie, K. G., Etim, E. U., Efiong, N. E., & Oleh, F. (2019). Spectroscopic Evaluation of Nitrate and Nitrite Concentrations in Selected Fruits and Vegetables. International Journal of Scientific Engineering and Science, 3(9), 32-35.
[8] Sharafati Chaleshtori, R., & Jadi, z. (2019). Fruits contaminated with lead, cadmium and nitrate are the risks to human health: A seasonal study. Iranian Journal of Toxicology, 13(4), 27-32. (In Farsi)
[9] Uddin, R., Thakur, M. U., Uddin, M. Z. & Islam, R. (2021). Study of nitrate levels in fruits and vegetables to assess the potential health risks in Bangladesh. Scientific Report, 11, 4704. https://doi.org/10.1038/s41598-021-84032-z
[10] Pascale, S. D., Maggio, A., Fogliano, V., Ambrosino, P., & Ritieni, A. (2001). Irrigation with saline water improves carotenoids content and antioxidant activity of tomato. The Journal of orticultural Science and Biotechnology, 76(4), 447-453.
[11] Hoff, J. E., and Wilcox, G. E. (1997). Accumulation of nitrate in tomato fruit and its effect on detaining. Journal of the American Society of Horticultural Science, 95, 92-4.
[12] Pourmoghim, M., Khosh Tinat, Kh., Sadeghi Barmaki, A., Komeili Fonod, R., Golestan, B., & Pirali, M. (2010). Determining amount of nitrate in letus, tomato and potato presented in Tehran wholesale market by HPLC. Iranian Journal of Nutrition Sciences and Food Technology, 1, 63-70. (in Farsi)
[13] Rezaei, M., Fani, A., Latif-Moini, A., Mirzajani, P., Malekirad, A. A., & Rafiei, M. 2014. Determining nitrate and nitrite content in beverages, fruits, vegetables and stews marketed in Arak, Iran. International Scholarly Research Notices. DOI: 10.1155/2014/439702. (in Farsi)
[14] Beheshti, M., Shahbazi, K., Bazargan, K., & Malekzadeh, E. (2019). Study of nitrate statues in tomatoes and cucmbers distributed in the Alborz province market. Alborz University of Medical Science Journal, 8(3), 281-299. (in Farsi)
[15] Shahbazzadegan S, Hashemimajd K, & Shahbazi B. (2010). Determination of nitrate concentration of consumed vegetables and fruits in Ardabil. Research Journal of Ardabil Medical Sciences, 10(1), 8-47.
[16] Petersen, A., & Stoltze, S. (2010). Nitrate and nitrite in vegetables on the Danish market: content and intake. Food Additives & Contaminants, 16(7), 291-299. https://doi.org/10.1080/026520399283957.
[17] Doomary, H., Kamkar, A., & Sharifi, H. (2017). Study of Nitrate content and the effective factors on it in the cucumbers of Jiroft area. Journal of Veterinary Research, 72(3), 363-373. (in Farsi)
[18] Hassani Moghaddam, E., Bazdar, A. R., Shaaban, M. (2019). Study of nitrate rate in some vegetables cultivated in Poldokhtar and Khorramabad, Lorestan Province. Iranian Journal of Health and Environment, 12(1), 101-112.
[19] Asadi, S., & Fazeli, F. (2020). Nitrate contents of some highly consumed products on sale in wholesale fruit and vegetable markets in spring and winter in District 4, Tehran, Iran. Scientific Journal of School of Public Health and Institute of Public Health Research, 18(1), 111-120.
[20] Fatemi Ghomsheh, A., & Nezami, S. (2020). Study of nitrate status in some vegetables collected from Kermanshah vegetables markets. Iranian Journal of Health and Environment, 13(1),77-86. (in Farsi)
[21] Seilsepour, M. (2020). Study of nitrate concentration in Varamin plain leafy vegetables and evaluation of its risk for human. Journal of Horticultural Plant Nutrition, 3(1), 69-86. (in Farsi)
[22] Huang, J., Pope, S., & Willis, M. (2019) A simple electrochemical method for nitrate determination in leafy vegetables. Journal of Human Nutrition, 3(1), 67-71.
[23] Delashad, M., Babalar, M., & Kashi, A. K. (2000). Effect of NH4/NH4+NO3 ratio of nutrient solutions on greenhouse tomato cultivars in hydroponic systems. Iranian Journal of Agricultural Science, 31(3), 613-625. (in Farsi)
[24] McMullen, S. E., Casanova, J. A., Gross, L. K., & Schenck, F. J. (2005). Ion chromatographic determination of nitraite and nitrit in vegetable and fruit baby foods. Journal of AOAC International, 88(6), 1793-1796.
[25] Campnella, B., Onor, M., & Pagliano, E. (2017). Rapid determination of nitrate in vegetables by gas chromatography mass spectrometry, Analytica Chimica Acta, doi: 10.1016/j.aca.2017.04.053.
[26] Matthew, N. B., Augustine, A. U., Shaibu, |S. E., Akpomie, K. G., Etim, A. U., Efiong, N. E., & Oleh, F. (2019) Spectroscopic evaluation of nitrate and nitrite concentrations in selected fruits and vegetables. International Journal of Scientific Engineering and Science, 3(9), 32-39.
[27] Tabande, L., & Zarei, M. (2018). Overview of nitrate concentration in some vegetables produced in Zanjan province. Journal of Soil Research, 32(3), 373-384. (in Farsi)
[28] Dumas, Y., Dadomo, M., Di Lucca, G., & Grolier, P. (2003). Effects of environmental factors and agricultural techniques on antioxidant content of tomatoes. Journal of the Science of Food and Agriculture, 83(5), 369-382.
[29] Nassiri, S. M., Khajavi, S., & Ramazanian, A. (2014). Application of image processing for determination of tomato color and lycopene content at different storing temperature. 1st National Conference on Harvest and Postharvest Novel Technologies of Agricultural Products. Mashhad, Iran. (in Farsi)
[30] Liu, C., Liu, W., Chen, W., Yang, J., & Zheng, L. (2015). Feasibility in multispectral imaging for predicting the content of bioactive compounds in intact tomato fruit. Food Chemistry, 173, 482-488.
[31] Zaborowicz, M., Boniecki, P., Koszela, K., Przybylak, A., & Przybyl, J. (2017). Application of neural image analysis in evaluating the quality of greenhouse tomatoes. Scientia Horticulturae, 218, 222-229.
[32] Dubey, S. R., & Jalal, A., S. (2015) Application of image processing in frui and vegetable analysis: A review. Journal of Intelligent Systems, 24(4), 405-424.
[33] Bhargava, A., & Bansal, A. (2018) Fruits and vegetables quality evaluation using computer vision: A review. Journal of King Saud University- Computer and Information Sciences, 33, 243-257.
[34] Mirra, K. B., Pooja, P., Ranchani, S., & Rajakumari, R. (2020) Fruit quality analysis using image processing. International Journal of Engineering and Advanced Technology, 9(5). 88-91.
[35] Riyaz, S., Venkatesh, T., Maheshwar Reddy, S., & Rahhika, K. (2022) Image processing based fruit and vegetables quality analysis on machine technology. International Journal of Research Publication and Reviews, 3(6), 3886-3890.
[36] Anonymous. (2006). Official Methods and Recommended Practices of the American Oil. Chemists Society (Ai 2-75, Bc 5-49, Bc 6-49, Da 15-48, Cc 17-95, and Da 14-48 methods) Champaign, IL: AOCS press. Retrieved from http://www.AOCS.org/methods.
[37] Hire, J. F., Anderson, R. E., Tatham, R. L., & Black, W. C. (2006). Multivariate Data Analysis. Pearson Education. New Delhi, India.
[38] Siniksaram, E. (2007). A Geometric interpretation of Mallows` Cp statistics and an alternative plot in variable selection. Computational Statistics and Data Analysis, 52, 3459-3467.
[39] Kazemi, A., Mohamed, A., shareef, H., & Zayandehroodi, H. (2013). Optimal power quality monitor placement using genetic algorithm and Mallow`s Cp. Electrical Power and Energy Systemms, 53, 564-575. (in Farsi)
[40] Gujarati, D. N. (2006). Basic Econometrics. Tata McGraw-Hill Publishing Company Ltd. New Delhi, India.
[41] Quej, V. H., Almorox, J., Ibrakhimov, M., & Saito, L. (2016). Empirical models for estimating daily global solar radiation in Yucatán Peninsula, Mexico. Energy Conversion and Management, 110, 448-456.
[42] Genel, K., Kurnaz, S. C., and Durman, M. (2003). Modeling of tribiological properties of alumina fiber reinforced zinc–aluminum composites using artificial neural network. Materials Science and Engineering, 363(2), 203-210.
[43] Deo, R. C., and Şahin, M. (2015). Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia. Atmospheric Research, 153, 512-525.
[44] Farzaneh, N., Golchin, A., & Hashemi Majd, K. (2010). Effect of different levels of nitrogen and potassium supplements on yield and concentration of N and K in tomato leaves. Journal of Science and Technology of Greenhouse Culture, 1, 27-33. (in Farsi)
[45] Jalini, M., & Dosti, F. (2012). Study of nitrate accumulation in potato and tomato products. Quarterly Journal of Environmental Science and Engineering, 50, 62-71. (in Farsi)
[46] Soto, F., Gallardo, M., Thompson, R.B., Peña-Fleitas, M.T., & Padilla, F.M. (2015). Consideration of total available N supply reduces N fertilizer requirement and potential for nitrate leaching loss in tomato production. Agriculture, Ecosystems & Environment, 20, 62-70.
[47] Gunes, A., Alpaslan, M., & Inal, A. (1998). Critical nutrient concentrations and antagonistic and synergistic relationships among the nutrients of NFT‐grown young tomato plants. Journal of Plant Nutrition, 21(10), 2035-2047.
[48] Ozores, M., Di Gioia, F., Sato, S., Simonne, E., & Morgan, K. (2015). Effects of nitrogen rates on nitrogen, phosphorous, and potassium partitioning, accumulation, and use efficiency in seepage-irrigated fresh market tomatoes. HortScience, 50(11), 1636-1643.
[49] Djidonou, D., Zhao, X., Simonne, E. H., Koch, K. E., & Erickson, J. E. (2013). Yield, water and nitrogen-use efficiency in field-grown, grafted tomatoes. HortScience, 48(4), 485-492.
[50] Tabande, L., & Safarzadeh Shirazi, S. (2018). Evaluation of nitrate accumulation and factors affecting it in some leafy vegetables in Zanjan province. Journal of Soil Research, 32(2), 189-201.
[51] Goel, N., & Sehgal, P. (2015). Fuzzy classification of pre-harvest tomatoes for ripeness estimation–An approach based on automatic rule learning using decision tree. Applied Soft Computing, 36, 45-56.
[52] Semary, N. A., Tharwat, A., Elhariri, E., & Hassanien, A. E. (2015). Fruit-based tomato grading system using features fusion and support vector machine. Intelligent Systems, 21, 401-410.