Investigation of Pennyroyal Plant Leaf Discoloration Classification in the Effect of Heavy Metals Absorption by Using Artificial Neural Networks (ANN) and Image Processing

Document Type : Original Article

Authors

1 M.Sc. of Mechanical Engineering of Biosystems Department, Razi University, Kermanshah, Iran

2 Assoc. Profe. of Mechanical Engineering of Biosystems Department, Razi University, Kermanshah, Iran

3 Assist. Profe. of Mechanical Engineering of Biosystems Department, Razi University, Kermanshah, Iran

4 Assist. Profe. of Production Engineering and Plant Genetics Department, Razi University, Kermanshah, Iran

5 Ph.D. of Mechanical Engineering of Biosystems Department, Razi University, Kermanshah, Iran

Abstract

Various methods are suggested for the removal and detection of heavy metals in the environment, most of which require a lot of time and money. Therefore, phytoremediation is a method that requires less time and money than other methods to remove heavy metals from the environment. In the present study, the image processing technique by smart mobile phone was used to determine the contamination of pennyroyal hyper accumulator plants by three heavy metals lead, nickel, and cadmium. Thirty plants were planted in thirty pots in perlite. For 28 days, these plants were photographed by mobile phones, both inside the box and contact imaging. Matlab R2017b software environment was used for image processing and artificial neural network operations. To determine the structure of artificial neural network, 12 neurons (Includes red, green and blue of RGB color space, hue, saturation and brightness of HSB color space, luminosity, blue Chroma and red Chroma of YCbCr color space and bright, red/green and bright yellow/blue L*a*b* color space) neurons as input layer and 4 neurons for output layer once (includes lead, nickel, cadmium, and control) again 2 neurons (containing heavy metal and control) in the output layer, both box and contact images were considered and the best network structure was identified.

Keywords


Beale, R. & Jackson, T. 1990. Neural Computing-an introduction. CRC Press.
Carral, E.; Puente, X.; Villares, R. & Carballeira, A. 1995. Background heavy metal levels in estuarine sediments and organisms in Galicia (northwest Spain) as determined by modal analysis. Science of the total environment, Vol. 172, pp. 175-88.
Chaney, R.; Malik, M.; Li, Y.; Brown, S.; Brewer, E. & Angle, J. 1997. Phytoremediation of soil metals. Current Opinion in Biotechnology Vol. pp. 279-284.
Di Natale, F.; Lancia, A.; Molino, A.; Di Natale, M.; Karatza, D. & Musmarra, D. 2006. Capture of mercury ions by natural and industrial materials. Journal of hazardous materials, 132(2-3), pp.220-225.
Giachetti, G. & Sebastiani, L. 2006. Metal accumulation in poplar plant grown with industrial wastes. Chemosphere, 64(3), pp.446-454.
Haghiabi, A. M.; Nasrolahi, A. H. & Parsaie, A. 2018. Water quality prediction using machine learning methods. Water Q Res J 53(1):3–13
Hong, Y.; Shen, R.; Cheng, H.; Chen, Y.; Zhang, Y.; Zhou, M.; Yu, L. & Liu, Y. 2019. Estimating lead and zinc concentrations in peri-urban agricultural soils through reflectance spectroscopy: Effects of fractional-order derivative and random forest. Science of the Total Environment, 651, pp.1969-1982.
Issac, A.; Srivastava, A.; & Dutta, M.K. 2019. An automated computer vision based preliminary study for the identification of a heavy metal (Hg) exposed fish-channa punctatus. Computers in biology and medicine, 111. https://doi.org/10.1016/j.compbiomed.2019.103326
Jun, S.; Xin, Z.; Xiaohong, W.; Bing, L.; Chunxia, D. & Jifeng, S. 2019. Research and analysis of cadmium residue in tomato leaves based on WT-LSSVR and Vis-NIR hyperspectral imaging. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 212, pp.215-221.
Lasat, M.M. 2002. Phytoextraction of toxic metals: a review of biological mechanisms. Journal of environmental quality, 31(1), pp.109-120.
Liu, M.; Liu, X.; Li, M.; Fang, M. & Chi, W. 2010. Neural-network model for estimating leaf chlorophyll concentration in rice under stress from heavy metals using four spectral indices. Biosyst Eng 106:223–233
Macek, T.; Francova, K.; Kochánková, L.; Lovecká, P.; Ryslava, E.; Rezek, J.; Sura, M.; Triska, J.; Demnerova, K. & Mackova, M. 2004. Phytoremediation—biological cleaning of a polluted environment. Reviews on environmental health, 19(1), pp.63-82.
Mendoza, F.; Dejmek, P. & Aguilera, J.M. 2006. Calibrated color measurements of agricultural foods using image analysis. Postharvest Biology and Technology, 41(3), pp.285-295.
Mohialden, K.M.; Omid, M.; Rajabipour, A.; Tajeddin, B. & Firouz, M.S. 2019. Quality and shelf-life prediction of cauliflower under modified atmosphere packaging by using artificial neural networks and image processing. Computers and Electronics in Agriculture, 163, pp.104861.
Patil, S.B. & Bodhe, S.K. 2011. Leaf disease severity measurement using image processing. International Journal of Engineering and Technology, 3(5), pp.297-301.
Salari, M.; Salami Shahid, E.; Afzali, S. H.; Ehteshami, M.; Conti, G. O.; Derakhshan, Z. & Sheibani, S. N. 2018. Quality assessment and artificial neural networks modeling for characterization of chemical and physical parameters of potable water. Food and Chemical Toxicology, 118, 212-219.
Shnbehzadeh, S.; Vahiddastjerdi, M.; Hasanzadeh, A. & Kianizadeh, T. 2014. Investigation of concentration of some heavy metals in water and sediment of Masjed Soleiman River before and after sewage entering it. Journal of Health System Research, 9(10), pp.1108-1116. (In Persian)
Sick, B. 2002. On-line and indirect tool wear monitoring in turning with artificial neural networks: a review of more than a decade of research. Mechanical systems and signal processing, 16(4), pp.487-546.
Vara Prasad, M.N. & de Oliveira Freitas, H.M. 2003. Metal hyper accumulation in plants: biodiversity prospecting for phytoremediation technology. Electronic journal of biotechnology, 6(3), pp.285-321.
Vesali, F.; Omid, M.; Kaleita, A. & Mobli, H. 2015. Development of an android app to estimate chlorophyll content of corn leaves based on contact imaging. Comput Electron Agric 116:211–220
Walker, E.L. & Connolly, E.L. 2008. Time to pump iron: iron-deficiency-signaling mechanisms of higher plants. Current opinion in plant biology, 11(5), pp.530-535.