Select the most appropriate morphologic characteristic to distinguish weeds in wheat fields by image processing technique

Document Type : Research Paper

Authors

Abstract

In order to select the most appropriate morphological characteristics of weeds in wheat fields in Khuzestan province, 16 species of the most common broadleaf weeds were selected.Collected species included: Ammi majus L., Anagallis spp., Beta vulgaris subsp. maritima (L.), Carthamus tinctorius L., Chenopodium murale L.,Convolvulus arvensis L, Lactuca serriola L., Malva spp.,Rumex dentatus L., Scorpiurus muricatus L., Silybum marianum L., Sinapis arvensis L., Sonchus tenerrimus L., Stelaria media L., Veronica persica Poir., and Vicia villosa Roth. For any species, five samples (as five replications) were photographed and images were analysed using image processing. Wheat, also, was photographed as control. After isolating images from background and tagging them, seven morphological characteristics including area, perimeter, aspect ratio (length to diameter ratio), rectangularity, area ratio of convex hull, perimeter ratio of convex hull, sphericity, form factor and eccentricity of each weed species and wheat were extracted. Results showed that the best morphological characteristics to distinguish broadleaf weeds from wheat were aspect ratio and sphericity. So that, compared to the weed species, aspect ratio was greatest (19.79) in wheat. After that, caterpillar-plant(9.71) and safflower (5.90) were greatest. The sphericity of wheat was the lowest (0.05). Considering the narrow shape of wheat leaves and the significant difference in leaf shape with broad-leaved species, this characteristic can be very useful for identifying and distinguishing wheat from broadleaf species at the field.

Keywords

References

Abdanan Mehdizadeh, S., Minaei, S., Mohajerani, E.,‌ Karimi Torshizi, M. A. 2014. Non-destructive assessment of egg freshness using UV-IR spectroscopy and determination of the effective wavelength domain. Iran. J. Biosys. Engng. 44: 101-112. (In Persian with English Summary).
Beckie, H.J., Heap, I.M., Smeda, R.J. and Hall. L.M.2000. Screening for herbicide resistance in Weeds. Weed Technol. 14: 428-445.
Bena Kashani, F., Zand, E. and Mohammad Alizadeh, H. 2006. Resistance of wild oat (Avena loduviciana) biotypes to clodinafop–propargyl herbicide. Entomol. Phytopath. 74: 127-149. (In Persian with English Summary).
Burgos-Artizzu, X.P., Ribeiro, A., Guijarro, M. and Pajares, G., 2011. Real-time image processing for crop-weed discrimination in maize fields. Comput. Electr. Agri. 75: 337–346.
Chauhan, B.S., and Johnson, D.E. 2010. The role of seed ecology in improving weed management strategies in the tropics. Adv Agron. 105: 221–262.
Dastoori, M., Rahimian, H., Zand, E., Mohammad Alizadeh, H., Maasoumi, M. and Bahrami, S. 2010. Molecular basis for resistance of Lolium rigidum populations to aryloxyphenoxy propionate herbicide through dCAPs. Iran. J. Field Crop Sci. 41: 677-684. (In Persian with English Summary).
Derakhshan, A. and Gherekhloo, J. 2012. Tribenuron-methyl resistant turnipweed (Rapistrum rugosum) from Iran. Proceedings of the 6th International Weed Science Congress, 17-22 June, Hangzhou, China.
Du, J. X., Wang, X. F. and zhang, G. J. 2007. Leaf shape based plant species recognition. Appl Math Comput. 185: 883-893.
Elahifard, E., Ghanbari, A., Rashed Mohassel, M.H., Zand, E., Mirshamsi Kakhki, A. and Mohkami, A. 2013. Characterization of triazine resistant biotypes of junglerice (Echinochloa colona (L.) Link.) found in Iran. Aust. J. Crop Sci. 7: 1302-1308.
Gan-Mor, S., Clark, R.L., 2001. DGPS-based automatic guidance-implementation and economical analysis. Trans. ASAE 01: 11–92.
Gherekhloo, J., Rashed Mohassel, M.H., Nasirri Mahallati, M., Zand, E., Ghanbari, A., Osuna, M.D. and De Prado, R. 2011. Confirmed resistance to aryloxyphenoxypropionate herbicides in Phalaris minor populations in Iran. Weed Biol Manage.11: 29-37.
Gonzalez-Andujar, J.L. 2009. Expert system for pests, diseases and weeds identification in olive crops. Expert Syst. Appl. 36: 3278-3283.
Han, S., Zhang, Q., Ni, B. and Reid, J.F. 2004. A guidance directrix approach to visionbased vehicle guidance systems. Comput. Electr. Agri. 43: 179–195.
Liao, S.H. 2005. Expert system methodologies and applications- A decade review from 1995 to 2004. Expert Syst. Appl. 28: 93-103.
Liebman, M., Mohler, C.L. and Staver, C.P. 2004. Ecological management of agricultural weeds. Ebook. Cambridge University Press. 532 Pp.
Mahaman, B.D., Harizanis, P., Filis, I., Antonopoulou, E., Yialouris, C.P. and Sideridis, A.B. 2002. A diagnostic expert system for honeybee pests.Comput. Electr. Agri. 36: 17-31.
Montalvo, M., Guerrero, J.M., Romeo, J., Emmi, L., Guijarro, M. and Pajares, G. 2013. Automatic expert system for weeds-crops identification in images from maize fields. Expert Syst. Appl. 40: 75–82.
Orak Chahartangi, H., Elahifard, E. and Abdanan Mehdizadeh, S. 2016 Morphological characteristics in order to identify the most appropriate choice eleven common weed species in Khuzestan province by using image processing technique. Proceeding of the 2nd National Conference on Agricultural Mechanization and New Technologies, 11-12 May, Mollasani, Ahvaz, Iran. (In Persian with English Summary).
Perez, A.J., Lopez, F., Benlloch, J.V. and Christensen, S. 2000. Colour and shape analysis techniques for weed detection in cereal fields. Comput. Electr. Agri. 25: 197–212.
Rastgoo, M., Rashed Mohassel, M.H., Zand, E. and Nassiri Mahallati, M. 2009. Seed bioassay to detect wild oat (Avena ludoviciana Dur.) resistant to clodinafop propargyl in Khuzestan wheat fields. Iran. J. Field Crops Res. 7: 421-430. (In Persian with English Summary).
Rao, A.N., Johnson, D.E., Sivaprasad, B., Ladha, J.K., and Mortimer, A.M. 2007. Weed management in direct-seeded rice. Adv Agron. 93:153–255.
SoltaniKazemi, M., Abdanan Mehdizadeh, S. and Gharineh, M.H. 2017. Dynamic force effects on germination characteristics and weight vigoure index of three chickpea cultivars (Cicer ariegtinum L.) seed by using image processing. Iranian J Seed Sci & Tech. 6: 177-192.
Stone, N.D., Coulson, R.N., Frisbie, R.E. and Loh, D.K. 1986. Expert systems in entomology: three approaches to problem solving. B. ESA. 32: 161-166.
Tellaeche, A., Pajares, G., Burgos-Artizzu, X.P. and Ribeiro, A. 2011. A computer vision approach for weeds identification through Support Vector Machines. Applied Soft Computing. 11: 908-915.
Yialouris, C.P. and Sideridis, A.B. 1996. An expert system for tomato diseases. Comput. Electr. Agri. 14: 61-76.
Zand, E., Baghestani, M.A., Dastaran, F., Atri, A.R., Labbafi, M.R., Khayami, M.M. and Porbaig, M. 2008. Investigation efficacy of some germinicides in control of resistant and susceptible ryegrass biotypes (Lolium rigidum L.) to acetyl coA carboxylase inhibiting herbicides. Plant Protec. 22: 129-145. (In Persian with English Summary).
Zimdahl, R.L.2007. Fundamentals of Weed Science. 3th edn. Academic Press, Elsevier Inc.666 Pp

            
Iranian Journal of Weed Science
Volume 13, Issue 2
January 2018
Pages 125-133

Files

Share

How to cite

Statistics