Intelligence System for Leaf Extraction and Disease Diagnostic
Keywords:
leaf extraction, contour analysis, marker controlled water shed segmentation, solidity measureAbstract
Agriculture encompasses agricultural production and the environmental goods and services. Plant species classification, recognition of medicinal value and identification of diseases are most important tasks in agriculture. For these applications a primary requirement is obtaining the target leaf. Thus, leaf extraction is an important step for variety of these applications. But it is still a challenging problem especially for the images with complicated background such as with some interference and overlaps between two adjacent leaves. Hence a leaf extraction algorithm has been developed using two approaches: contour analysis approach and marker controlled watershed segmentation method. The contour analysis approach employs contour regions to detect the boundaries of the objects. The target leaf is obtained using the connected edges of the contour boundary. The second approach, marker-controlled watershed segmentation method is applied on the gradient images of Hue, Intensity and Saturation of the HSI color space, separately. The solidity (integrity) measure is then used to evaluate how well the segmented image is for extraction of the target leaf and determine the final leaf extraction result. The extracted leaf is given as an input to the disease diagnosis system for analysis of disease on the given leaf.
References
Xiaodong Tang, Manhua Liu, Hui Zhao, Wei Tao Department of Instrument Science & Engineering, School of EIEE Shanghai Jiao Tong University Shanghai, PRC “Leaf Extraction from Complicated Background”
Joao Camargo Neto, George E. Meyer, and David D. Jones, “Individual leaf extractions from young canopy images using Gustafson-Kessel clustering and a genetic algorithm”, Computers and electronics in agriculture 51, Elsevier, USA, 2006, 66-85.
Franz. E., Gaultney, L.D., and Unklesbay, K.B., “Algorithms for extraction leaf boundary information from digital images of plant foliage”, Trans, ASAE 38(2), USA, 1995, pp. 625-633.
]Franz. E., Gebhardt, M.R., and Unklesbay, K.B., “Shape description of completely visible and partially occluded leaves fro identifying plants in digital images”, Trans, ASAE 4(2), USA, 1991, pp. 673-681.
Xiao-Feng Wang, De-Shuang Huang, Ji-Xiang Du, Huan Xu , Laurent Heutte, “Classification of plant leaf images with complicated background,” Applied Mathematics and Computation, 205(2), pp. 916-926, 2008.
Woebbeck, D.M., Meyer, G.E., VonBargen, K., and Mortensen, D.A.,“Color indices for weed identification under various soil, residue and lighting conditions”, Trans. ASAE 38, USA, 1995, pp. 259-269.
Otsu, N., "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, No. 1, 1979, USA, pp. 62-66.
Otsu, N., "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, No. 1, 1979, pp. 62-66.
Seber, G. A. F. Multivariate Observations. Hoboken, NJ: John Wiley & Sons, Inc., 1984.
Spath, H. Cluster Dissection and Analysis: Theory, FORTRAN Programs, Examples. Translated by J. Goldschmidt. New York: Halsted Press, 1985.
Rafael C. Gonzalez, Richard E. Woods, and Steven L. Eddins, Digital Image Processing using MATLAB, Publishing House of Electronics Industry, Beijing, 2004.
www.mathworks.com
www.ni.com/LabVIEW/
www.stackoverflow.com
www.wikipedia.com
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
