Advanced SearchSearch Tips
Band Selection Using Forward Feature Selection Algorithm for Citrus Huanglongbing Disease Detection
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
  • Journal title : Journal of Biosystems Engineering
  • Volume 40, Issue 4,  2015, pp.417-427
  • Publisher : Korean Society for Agricultural Machinery
  • DOI : 10.5307/JBE.2015.40.4.417
 Title & Authors
Band Selection Using Forward Feature Selection Algorithm for Citrus Huanglongbing Disease Detection
Katti, Anurag R.; Lee, W.S.; Ehsani, R.; Yang, C.;
  PDF(new window)
Purpose: This study investigated different band selection methods to classify spectrally similar data - obtained from aerial images of healthy citrus canopies and citrus greening disease (Huanglongbing or HLB) infected canopies - using small differences without unmixing endmember components and therefore without the need for an endmember library. However, large number of hyperspectral bands has high redundancy which had to be reduced through band selection. The objective, therefore, was to first select the best set of bands and then detect citrus Huanglongbing infected canopies using these bands in aerial hyperspectral images. Methods: The forward feature selection algorithm (FFSA) was chosen for band selection. The selected bands were used for identifying HLB infected pixels using various classifiers such as K nearest neighbor (KNN), support vector machine (SVM), naïve Bayesian classifier (NBC), and generalized local discriminant bases (LDB). All bands were also utilized to compare results. Results: It was determined that a few well-chosen bands yielded much better results than when all bands were chosen, and brought the classification results on par with standard hyperspectral classification techniques such as spectral angle mapper (SAM) and mixture tuned matched filtering (MTMF). Median detection accuracies ranged from 66-80%, which showed great potential toward rapid detection of the disease. Conclusions: Among the methods investigated, a support vector machine classifier combined with the forward feature selection algorithm yielded the best results.
Bayesian classification;Hyperspectral;K nearest neighbor;Multi-modal Bayesian classification;Support vector machine;
 Cited by
Albritton, M. 2012. Sections (TRS) positive for Huang-longbing (HLB, Citrus Greening) in Florida. Available at:

Bajwa, S. G., P. Bajcsy, P. Groves and L. F. Tian. 2004. Hyperspectral image data mining for band selection in agricultural applications. Transactions of the ASAE 47(3):895-907. crossref(new window)

Boardman, J. W. and F. A. Kruse. 1994. Automated spectral analysis: A geologic example using AVIRIS data, north Grapevine Mountains, Nevada. In: Proceedings of the Thematic Conference on Geologic Remote Sensing 10(1):407-418.

Brlansky, R. H., K. R. Chung and M. E. Rogers. 2005. 2006 Florida citrus pest management guide: Huanglongbing (citrus greening). UF/IFAS Extension.

Candade, N. and B. Dixon. 2004. Multispectral classification of Landsat images: A comparison of support vector machine and neural network classifiers. ASPRS Annual Conference Proceedings, Denver, Colorado.

Cestnik, B. 1990. Estimating probabilities: a crucial task in machine learning. In: Proceedings of the European Conference on Artificial Intelligence, pp. 147-149, Stockholm, Sweden,.

Cover, T. and P. Hart. 1967. Nearest neighbour pattern classification. IEEE Transactions on Information Theory 13(1):21-27. crossref(new window)

Demir, B. and S. Erturk. 2007. Hyperspectral image classification using relevance vector machines. IEEE Transactions on Geoscience and Remote Sensing Letters, 4(4):586-590. crossref(new window)

Garnier, M., S. Jagoueix-Eveillard, P. R. Cornje, H. F. Le Roux and J. M. Bove. 2000. Genomic characterization of a Liberibacter present in an ornamental rutaceous tree, Calodendrum capense, in the Western Cape province of South Africa. Proposal of 'Candidatus Liberibacter africanus subsp. capensis'. International Journal of Systematic and Evolution Microbiolog 50:2119-2125. crossref(new window)

Huang, W., D. W. Lamb, Z. Niu, Y. Zhang, L. Liu and J. Wang. 2007. Identification of yellow rust in wheat using in-situ spectral reflectance measurements and airborne hyperspectral imaging. Precision Agriculture 8(4-5):187-197. crossref(new window)

Kong, W., C. Zhang, F. Liu, P. Nie and Y. He. 2013. Rice seed cultivar identification using near-infrared hyperspectral imaging and multivariate data analysis. Sensors 13:8916-8927. crossref(new window)

Kumar, A., W. S. Lee, R. Ehsani, L. G. Albrigo, C. Yang and R. L. Mangan. 2012. Citrus greening disease detection using aerial hyperspectral and multispectral imaging techniques. Journal of Applied Remote Sensing 6, 063542. crossref(new window)

Kumar, S., J. Ghosh and M. M. Crawford. 2001. Best-bases feature extraction algorithms for classification of hyperspectral data. IEEE Trans. Geosci. Remote Sens 39(7):1368-1379. crossref(new window)

Kuo, B., J. Yang, T. Sheu and S. Yang. 2008. Kernel-based KNN and Gaussian classifiers for hyperspectral image classification. Geoscience and Remote Sensing Symposium, IEEE International, II-1006-II-1008.

Li, X., W. S. Lee, M. Li, R. Ehsani, A. R. Mishra and C. Yang. 2012. Spectral difference analysis and airborne imaging classification for citrus greening infected trees. Computers and Electronics in Agriculture 83:32-46. crossref(new window)

Matsuo, K., M. Iwate, K. Nishiwaki, S. Zhang and M. Yashiro. 2006. Development of experimental setup for distinction of disease plant. ASABE Paper No. 063016, St. Joseph, Mich.: ASABE.

Melgani, F. and L. Bruzzone. 2004. Classification of hyperspectral remote-sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing 42(8):1778-1790. crossref(new window)

Sankaran, S., A. Mishra, R. Ehsani and C. Davis. 2010. A review of advanced techniques for detecting plant diseases. Computers and Electronics in Agriculture 72(1):1-13. crossref(new window)

Shafri, H. Z. M. and N. Hamdan. 2009. Hyperspectral imagery for mapping disease infection in oil palm plantation using vegetation indices and red edge techniques. American Journal of Applied Sciences 6(6):1031-1035. crossref(new window)

Qin, J., T. F. Burks, M. A. Ritenour and W. G. Bonn. 2009. Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence. Journal of Food Engineering 93:183-191. crossref(new window)

Qin, Z. and M. Zhang. 2005. Detection of rice sheath blight for in-season disease management using multispectral remote sensing. International Journal of Applied Earth Observation and Geoinformation 115-128.

Rouse, J. W., R. H. Haas, J. A. Schell and D. W. Deering. 1973. Monitoring vegetation systems in the Great Plains with ERTS. Third ERTS Symposium, NASA SP-351 I: 309-317.

USDA. 2012. 2010-2011 Citrus summary. Available at:

Whitney, A. W. 1971. A direct method of nonpa rametric measurement selection. IEEE Transactions on Computers 20: 1100-1103.

Williams, P. J., P. Geladi, T. J. Britz and M. Manley. 2012. Near-infrared (NIR) hyperspectral imaging and multivariate image analysis to study growth characteristics and differences between species and strains of members of the genus Fusarium. Analytical and Bioanalytical Chemistry 404: 1759-1769. crossref(new window)

Yang, C. 2010. An airborne four-camera imaging system for agricultural applications. ASABE Paper No. 1008855, St. Joseph, Mich.: ASABE.

Yang, C. M. 2010. Assessment of the severity of bacterial leaf blight in rice using canopy hyperspectral reflectance. Precision Agriculture 11:61-81. crossref(new window)

Yang, C., J. H. Everitt, M. R. Davis and C. Mao. 2003. A CCD camera-based hyperspectral imaging system for stationary and airborne applications. Geocarto International 18(2):71-80. crossref(new window)