Detection for Corn/Weed Images Using Moment Invariants by BPNN Classifier

Abstract:

This study was conducted to discriminate the weed from the corn in a field combined neural network classifier with image processing technology. The corn and weed images were scanned using a colour imaging system. In the first step, an approximate location of the object of interest was determined by minimum enclosing rectangle, in which image processing was done to obtain the binary image. In the second step, the seven invariant moments were extracted from binary images and used as input to the back propagation neural network (BPNN) classifier. The training set was used to construct shape model representing the objects. The detection accuracy was enhanced by adjusting the number of neurons in the network. Experimental results showed that the BPNN classifier achieved overall detection accuracy of 94.52% with 7-28-1.

• Periodical: Advanced Materials Research (Volumes 605-607)
• Pages: 2183-2186
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.605-607.2183
• Online since: December 2012
• Authors: Lan Lan Wu, Jie Wu, You Xian Wen, Hui Peng, Zhi Hui Zhu
• Keywords: Image Processing, Moment Invariants, Neural Network Classifier, Weed

References

[1] Sogaard H T and Olsen H J. Determination of crop rows by image analysis without segmentation. Comput. Electron. Agr. Vol. 38(2005), pp.141-158.

[2] Tellaeche A, Burgos-Artizzu X P, Pajares G and Ribeiro A. A vision-based method for weeds identification through the Bayesian decision theory. Pattern Recogn. Vol. 42(2008) pp.521-530.

DOI: 10.1016/j.patcog.2007.07.007

[3] Pe´reza A J, Lopeza F, Benllocha J V and Christensen S. Color and shape analysis techniques for weed detection in cereal fields. Comput. Electron. Agr. Vol. 25(2000), pp.197-212.

[4] Burks T F, Shearer S A, Heath J R and Donohue K D 2005. Evaluation of neural-network classifiers for weed species discrimination. Biosyst. Eng. Vol. 91(2005), pp.293-304.

DOI: 10.1016/j.biosystemseng.2004.12.012

[5] Lanlan Wu and Youxian Wen. Weed/corn seedling recognition by support vector machine using texture features. African J Agr. Res. Vol. 9(2009), pp.840-846.

DOI: 10.1109/icise.2010.5689900

[6] Hemming J and Rath T. Computer-Vision-based weed identification under field conditions using controlled lighting. Precis. Agric. Vol. 78(2001), pp.233-243.

[7] Sena-Jr D G, Pinto F A C, Queiroz D M andViana P A. Fall armyworm damaged maize plant identification using digital images. Biosyst. Eng. Vol. 85(2003), pp.449-454.

DOI: 10.1016/s1537-5110(03)00098-9

[8] Ishak A J, Hussain A and Marzuki M. Mustafa weed image classification using Gabor wavelet and gradient field distribution. Comput. Electron. Agr. Vol. 66(2009), pp.53-61.

DOI: 10.1016/j.compag.2008.12.003

[9] Meyer G E and Camargo-Neto J. Verification of colour vegetation indices for automated crop imaging applications. Comput. Electron. Agr. Vol. 63(2008), pp.282-293.

DOI: 10.1016/j.compag.2008.03.009

[10] Hu M K. Visual pattern recognition by moment invariant. IEEE T Inform. Theory. Vol. 2(1962), pp.179-187.