Abstract—In this paper we evaluate the quality of segmentation of plant images achieved by different level set methods commonly used in the literature. The plants of study are narrow-leaf cereal plants at different growth stages and the segmentation quality measure was considered to be the boundary, leaf tips, and axils. The results show that region-based level set methods can perform the segmentation of plants with high accuracy when the plants are at either early or mature stages of growth. The results also show that contour based level set algorithms are not applicable to the segmentation of narrow leaf plants because the front being computed does not advance to the high curvature features, such as sharp tips and axils. A typical image of a mature plant has isolated regions from the interlacing of leaves. Only region-based methods can perform the segmentation with good accuracy. Level set methods are sensitive to initialization and parameter selection.
Index Terms—Active Contour, Image Segmentation, Level Set, Narrow-Leaf plants.
M. R. Golzarian is with the Phenomics and Bioinformatics Research Centre, University of South Australia, Mawson Lakes, SA5095, Australia. He is also an academic member of the Department of Agricultural Engineering-Agricultural Machinery, Faculty of Agriculture, Ferdowsi University of Mashhad, Iran. Corresponding author: Tel: +61 8 83026982;Fax: +61 8 83025785; Email: Mahmood.Golzarian@unisa.edu.au
J. Cai is with the Phenomics and Bioinformatics Research centre, School of Mathematics and Statistics, University of South Australia, Mawson Lakes, Adelaide SA5095, Australia. Email: Jinhai.Cai@unisa.edu.au
R. A. Frick is a lecturer and research fellow School of Mathematics and Statistics, University of South Australia and the Australian Centre for Plant Functional Genomics. Email: Ross.Frick@unisa.edu.au.
S. J. Miklavcic is with the Phenomics and Bioinformatics Research centre, School of Mathematics and Statistics, University of South Australia, Mawson Lakes, SA 5095, Australia. He is also a member of Department of Science and Technology, University of Linkoping, Norrkoping, Sweden, and Australian Centre for Plant Functional Genomics Pty Ltd, Adelaide, SA 5064, Australia. Email: Stan.Miklavcic@unisa.edu.au.
Cite: Mahmood R. Golzarian, Jinhai Cai, Ross A. Frick, and Stan J. Miklavcic, "Segmentation of Cereal Plant Images Using Level Set Methods – A Comparative Study," International Journal of Information and Electronics Engineering vol. 1, no. 1, pp. 72-78 , 2011.