Hostname: page-component-77c89778f8-cnmwb Total loading time: 0 Render date: 2024-07-17T03:54:49.406Z Has data issue: false hasContentIssue false

Seed classification of three species of amaranth (Amaranthus spp.) using artificial neural network and canonical discriminant analysis

Published online by Cambridge University Press:  27 September 2019

A. Bagheri*
Affiliation:
Department of Agronomy and Plant Breeding, Razi University, Kermanshah, Iran
L. Eghbali
Affiliation:
Department of Agronomy and Plant Breeding, Azad University, Mashhad, Iran
R. Sadrabadi Haghighi
Affiliation:
Department of Agronomy and Plant Breeding, Azad University, Mashhad, Iran
*
Author for correspondence: A. Bagheri, E-mail: alireza884@gmail.com

Abstract

The current study was conducted in 2013 to identify the seeds of three species of Amaranthus, Amaranthus viridis L., Amaranthus retroflexus L. and Amaranthus albus L., by using the artificial neural network (ANN) and canonical discriminant analysis (CDA) methods. To begin with, photographs were taken of the seeds and 13 morphological characteristics of each seed extracted as predictor variables. Backward regression was used to find the most influential variables and seven variables were derived. Thus, predictor variables were divided into two sets of 13 and seven morphological characteristics. The results showed that the recognition accuracy of the ANN made using 13 and seven predictor variables was 81.1 and 80.3%, respectively. Meanwhile, recognition accuracy of the CDA using the seven and 13 predictor variables was 74.0 and 75.7%, respectively. Therefore, in comparison to CDA, ANN showed higher identification accuracy; however, the difference was not statistically significant. Identification accuracy for A. retroflexus was higher using the CDA method than ANN, while the ANN method had higher recognition accuracy for A. viridis than CDA. In addition, use of 13 predictor variables yielded a greater identification accuracy than seven. The results of the current study showed that using seed morphological characteristics extracted by computer vision could be effective for reliable identification of the similar seeds of Amaranthus species.

Type
Crops and Soils Research Paper
Copyright
Copyright © Cambridge University Press 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Alvarez, R (2009) Predicting average regional yield and production of wheat in the Argentine Pampas by an artificial neural network approach. European Journal of Agronomy 30, 7077.Google Scholar
Amari, S, Murata, N, Muller, KR, Finke, M and Yang, HH (1997) Asymptotic statistical theory of overtraining and cross-validation. IEEE Transactions on Neural Networks 8, 985996.Google Scholar
Anouar, F, Mannino, MR, Casals, ML, Fougereux, JA and Demilly, D (2001) Carrot seeds grading using a vision system. Seed Science and Technology 29, 215225.Google Scholar
Ashraf, B, Yazdani, R, Mousavi-Baygi, M and Bannayan, M (2014) Investigation of temporal and spatial climate variability and aridity of Iran. Theoretical and Applied Climatology 118, 3546.Google Scholar
Benedetti, S, Mannino, S, Sabatini, AG and Marcazzan, GL (2004) Electronic nose and neural network use for the classification of honey. Apidologie 35, 397402.Google Scholar
Cervantes, E, Martín, JJ and Saadaoui, E (2016) Updated methods for seed shape analysis. Scientifica 2016, 110. http://dx.doi.org/10.1155/2016/5691825.Google Scholar
Chen, X, Xun, Y, Li, W and Zhang, J (2010) Combining discriminant analysis and neural networks for corn variety identification. Computers and Electronics in Agriculture 71(suppl. 1), S48S53.Google Scholar
Chen, G, Bui, TD, Krzyzak, A and Krishnan, S (2013) Small bowel image classification based on Fourier-Zernike moment features and canonical discriminant analysis. Pattern Recognition and Image Analysis 23, 211216.Google Scholar
Chow, CK (1965) Statistical independence and threshold functions. IEEE Transactions on Electronic Computers EC-14, 6668.Google Scholar
Chtioui, Y, Bertrand, D, Dattée, Y and Devaux, MF (1996) Identification of seeds by colour imaging: comparison of discriminant analysis and artificial neural network. Journal of the Science of Food and Agriculture 71, 433441.Google Scholar
Chtioui, Y, Bertrand, D and Barba, D (1998) Feature selection by a genetic algorithm. Application to seed discrimination by artificial vision. Journal of the Science of Food and Agriculture 76, 7786.Google Scholar
Dana, W and Ivo, W (2008) Computer image analysis of seed shape and seed color for flax cultivar description. Computers and Electronics in Agriculture 61, 126135.Google Scholar
Dehghan-Shoar, M, Hampton, J and Haslett, S (1998) Identification of, and discrimination among, lucerne (Medicago sativa L.) varieties using seed image analysis. Plant Varieties & Seeds 11, 107127.Google Scholar
Dubey, BP, Bhagwat, SG, Shouche, SP and Sainis, JK (2006) Potential of artificial neural networks in varietal identification using morphometry of wheat grains. Biosystems Engineering 95, 6167.Google Scholar
Eizenga, GC, Ali, ML, Bryant, RJ, Yeater, KM, McClung, AM and McCouch, SR (2014) Registration of the Rice Diversity Panel 1 for genomewide association studies. Journal of Plant Registrations 8, 109116.Google Scholar
Fawzi, NM, Fawzy, AM and Mohamed, AAA (2010) Seed morphological studies on some species of Silene l. (Caryophyllaceae). International Journal of Botany 6, 287292.Google Scholar
Gardarin, A, Dürr, C and Colbach, N (2009) Which model species for weed seedbank and emergence studies? A review. Weed Research 49, 117130.Google Scholar
Granitto, PM, Navone, HD, Verdes, PF and Ceccatto, HA (2002) Weed seeds identification by machine vision. Computers and Electronics in Agriculture 33, 91103.Google Scholar
Granitto, PM, Verdes, PF and Ceccatto, HA (2005) Large-scale investigation of weed seed identification by machine vision. Computers and Electronics in Agriculture 47, 1524.Google Scholar
Guisan, A and Theurillat, JP (2000) Assessing alpine plant vulnerability to climate change: a modeling perspective. Integrated Assessment 1, 307320.Google Scholar
Horak, MJ and Loughin, TM (2009) Growth analysis of four Amaranthus species. Weed Science 48, 347355.Google Scholar
Horak, MJ, Peterson, DE, Chessman, DJ and Wax, LM (1994) Pigweed Identification: A Pictorial Guide to the Common Pigweeds of the Great Plains. Manhattan, KS, USA: Kansas State University Agricultural Experiment Station and Cooperative Extension Service.Google Scholar
Hoyo, Y and Tsuyuzaki, S (2013) Characteristics of leaf shapes among two parental Drosera species and a hybrid examined by canonical discriminant analysis and a hierarchical Bayesian model. American Journal of Botany 100, 817823.Google Scholar
Jain, AK, Duin, RPW and Mao, J (2000) Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 437.Google Scholar
Kasabov, NK (1996) Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering. Cambridge, MA, USA: MIT Press.Google Scholar
Khemiri, S, Gaamour, A, Ben Abdallah, L and Fezzani, S (2018) The use of otolith shape to determine stock structure of Engraulis encrasicolus along the Tunisian coast. Hydrobiologia 821, 7382.Google Scholar
Kohonen, T (2012) Self-Organization and Associative Memory. Springer Series in Information Sciences no. 8. Germany, Berlin: Springer Berlin Heidelberg.Google Scholar
Li, L, Boyd, CE, Odom, J and Dong, S (2013) Identification of ictalurid catfish fillets to rearing location using elemental profiling. Journal of the World Aquaculture Society 44, 405414.Google Scholar
Li, X, Zecchin, AC and Maier, HR (2014) Selection of smoothing parameter estimators for general regression neural networks – Applications to hydrological and water resources modelling. Environmental Modelling & Software 59, 162186.Google Scholar
Li, X, Maier, HR and Zecchin, AC (2015) Improved PMI-based input variable selection approach for artificial neural network and other data driven environmental and water resource models. Environmental Modelling & Software 65, 1529.Google Scholar
Liu, ZY, Cheng, F, Ying, YB and Rao, XQ (2005) Identification of rice seed varieties using neural network. Journal of Zhejiang University: Science B 6, 10951100.Google Scholar
Lovelli, S, Perniola, M, Ferrara, A, Amato, M and Di Tommaso, T (2010) Photosynthetic response to water stress of pigweed (Amaranthus retroflexus) in a southern-Mediterranean area. Weed Science 58, 126131.Google Scholar
Majumdar, S and Jayas, DS (2000) Classification of cereal grains using machine vision: I. Morphology models. Transactions of the ASAE 43, 16691675.Google Scholar
Marini, F, Zupan, J and Magrì, AL (2004) On the use of counterpropagation artificial neural networks to characterize Italian rice varieties. Analytica Chimica Acta 510, 231240.Google Scholar
Masters, T (1993) Practical Neural Network Recipes in C++. San Diego, USA: Academic Press.Google Scholar
Monteiro, RVA, Guimarães, GC, Moura, FAM, Albertini, MRMC and Albertini, MK (2017) Estimating photovoltaic power generation: performance analysis of artificial neural networks, Support Vector Machine and Kalman filter. Electric Power Systems Research 143, 643656.Google Scholar
Olesen, MH, Carstensen, JM and Boelt, B (2011) Multispectral imaging as a potential tool for seed health testing of spinach (Spinacia oleracea L.). Seed Science and Technology 39, 140150.Google Scholar
Olesen, MH, Nikneshan, P, Shrestha, S, Tadayyon, A, Deleuran, LC, Boelt, B and Gislum, R (2015) Viability prediction of Ricinus cummunis L. seeds using multispectral imaging. Sensors (Switzerland) 15, 45924604.Google Scholar
Onyango, CM and Marchant, JA (2003) Segmentation of row crop plants from weeds using colour and morphology. Computers and Electronics in Agriculture 39, 141155.Google Scholar
OuYang, A, Gao, R, Liu, Y, Sun, X, Pan, Y and Dong, X (2010) An automatic method for identifying different variety of rice seeds using machine vision technology. In Yue, S, Wei, HL, Wang, L and Song, Y (eds), Sixth International Conference on Natural Computation (ICNC). Yantai, Shandong, China: Institute of Electrical and Electronics Engineers, pp. 8488.Google Scholar
Padonou, EA, Kassa, B, Assogbadjo, AE, Fandohan, B, Chakeredza, S, Glèlè Kakaï, R and Sinsin, B (2014) Natural variation in fruit characteristics and seed germination of Jatropha curcas in Benin, West Africa. Journal of Horticultural Science and Biotechnology 89, 6973.Google Scholar
Paliwal, J, Visen, NS and Jayas, DS (2001) AE – automation and emerging technologies: evaluation of neural network architectures for cereal grain classification using morphological features. Journal of Agricultural Engineering Research 79, 361370.Google Scholar
Perez, AJ, Lopez, F, Benlloch, JV and Christensen, S (2000) Colour and shape analysis techniques for weed detection in cereal fields. Computers and Electronics in Agriculture 25, 197212.Google Scholar
Pometti, CL, Bessega, CF, Vilardi, JC, Ewens, M and Saidman, BO (2016) Genetic variation in natural populations of Acacia visco (Fabaceae) belonging to two sub-regions of Argentina using AFLP. Plant Systematics and Evolution 302, 901910.Google Scholar
Qiu, M, Song, Y and Akagi, F (2016) Application of artificial neural network for the prediction of stock market returns: the case of the Japanese stock market. Chaos, Solitons & Fractals 85, 17.Google Scholar
Ramchoun, H, Idrissi, MAJ, Ghanou, Y and Ettaouil, M (2017) New modeling of multilayer perceptron architecture optimization with regularization: an application to pattern classification. IAENG International Journal of Computer Science 44, 261269.Google Scholar
Ronge, RV and Sardeshmukh, M (2014) Comparative analysis of Indian wheat seed classification. In 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI). Piscataway, NJ, USA: IEEE, pp. 937942.Google Scholar
Roy, S, Marndi, BC, Mawkhlieng, B, Banerjee, A, Yadav, RM, Misra, AK and Bansal, KC (2016) Genetic diversity and structure in hill rice (Oryza sativa L.) landraces from the North-Eastern Himalayas of India. BMC Genetics 17, 115. doi: 10.1186/s12863-016-0414-1.Google Scholar
Şeker, ŞS and Şenel, G (2017) Comparative seed micromorphology and morphometry of some orchid species (Orchidaceae) belong to the related Anacamptis, Orchis and Neotinea genera. Biologia (Poland) 72, 1423.Google Scholar
Sellers, BA, Smeda, RJ, Johnson, WG, Kendig, JA and Ellersieck, MR (2003) Comparative growth of six Amaranthus species in Missouri. Weed Science 51, 329333.Google Scholar
Shrestha, S, Deleuran, LC, Olesen, MH and Gislum, R (2015) Use of multispectral imaging in varietal identification of tomato. Sensors (Switzerland) 15, 44964512.Google Scholar
Slaughter, DC, Giles, DK and Downey, D (2008) Autonomous robotic weed control systems: a review. Computers and Electronics in Agriculture 61, 6378.Google Scholar
Snyder, WE and Qi, H (2010) Machine Vision. Cambridge, UK: Cambridge University Press.Google Scholar
Tellaeche, A, Pajares, G, Burgos-Artizzu, XP and Ribeiro, A (2011) A computer vision approach for weeds identification through Support Vector Machines. Applied Soft Computing 11, 908915.Google Scholar
Tungmunnithum, D, Boonkerd, T, Zungsontiporn, S and Tanaka, N (2016) Morphological variations among populations of Monochoria vaginalis s.l. (Pontederiaceae) in Thailand. Phytotaxa 268, 5768.Google Scholar
van Evert, FK, Fountas, S, Jakovetic, D, Crnojevic, V, Travlos, I and Kempenaar, C (2017) Big Data for weed control and crop protection. Weed Research 57, 218233.Google Scholar
Velásco-Mejía, A, Vallejo-Becerra, V, Chávez-Ramírez, AU, Torres-González, J, Reyes-Vidal, Y and Castañeda-Zaldivar, F (2016) Modeling and optimization of a pharmaceutical crystallization process by using neural networks and genetic algorithms. Powder Technology 292, 122128.Google Scholar
Venora, G, Grillo, O, Shahin, MA and Symons, SJ (2007) Identification of Sicilian landraces and Canadian cultivars of lentil using an image analysis system. Food Research International 40, 161166.Google Scholar
Xinshao, W and Cheng, C (2015) Weed seeds classification based on PCANet deep learning baseline. In 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA). Hong Kong: Asia-Pacific Signal and Information Processing Association, pp. 408415.Google Scholar