Title: Crop and weed discrimination in agricultural field using MRCSF

Authors: R.S. Sabeenian, V. Palanisamy

Addresses: Centre Head-Sona SIPRO, Advanced Research Centre, Sona College of Tech., Sona Nagar, TPT Road, Salem 636005, Tamil Nadu, India. ' Info Institute of Engineering, Sathy Road, Kovil Palayam, Coimbatore 641 107, Tamil Nadu, India

Abstract: Texture classification is a chic and trendy technology in image processing. Weed control is a major effect on agriculture. Large amount of herbicide has been used for controlling weeds. Certain areas in the agricultural field have more weeds. So, we require an automated visual system that can discriminate weeds from a given field image, which will reduce or even eliminate the amount of herbicide used. This would help farmers to use herbicides only in places where required. In this paper, Multiresolution Combined Statistical and Spatial Frequency (MRCSF) is used to discriminate the weeds from the crops and to classify them.

Keywords: texture classification; crop images; weed images; MRCSF; multiresolution combined statistical and spatial frequency; MRFM; Markov random field matrix; weed detection; spatial frequency; image processing; weed control; automated visual systems; vision automation; agriculture.

DOI: 10.1504/IJSISE.2010.034633

International Journal of Signal and Imaging Systems Engineering, 2010 Vol.3 No.1, pp.61 - 69

Received: 05 Sep 2009
Accepted: 19 Feb 2010
Published online: 13 Aug 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article