Current Science

Open Access Open Access  Restricted Access Subscription Access

Wavelength Selection and Classification of Hyperspectral Non-Imagery Data to Discriminate Healthy and Unhealthy Vegetable Leaves


Affiliations
1 Department of Information Technology, Government College of Engineering, Aurangabad 431 005, India
2 Department of Computer Science and Information Technology, Dr B.A.M. University, Aurangabad 431 005, India
 

Being the largest vegetarian population across the globe, vegetables are an integral part of Indian meals. The proposed research finds significant wavelengths to discriminate healthy and unhealthy vegetable plants. Spectral-reflectance (SR) and first-derivative (FD) in the visible, red edge and near infrared region (350–1000 nm) of three vegetables brinjal, cluster beans and long beans were used. The significant wavelengths were selected using ReliefF and Support- Vector-Machine (SVM). Random forest algorithm was used for classification. The binary classification was used for each vegetable separately, and multiclass classification was applied for all the samples. The most significant spectral wavelengths, for the prediction of diseased brinjal, correspond primarily to the red edge in SR. Long beans samples were classified accurately in the red-edge. In the case of cluster beans, SR is more effective than FD in the red-edge. The results substantiate the utility of HS data for discrimination of healthy and unhealthy vegetable plants and even vegetable types.

Keywords

Classification Accuracy, Healthy and Unhealthy Vegetable Plants, Hyperspectral Measurements, Spectral Reflectance, Wavelength Selection.
User
Notifications
Font Size

  • Thenkabail, P. S. et al., Selection of hyperspectral narrowbands (HNBs) and composition of hyperspectral twoband vegetation indices (HVIs) for biophysical characterization and discrimination of crop types using field reflectance and hyperion/EO-1 data. IEEE J. Select. Top. Appl. Earth Obs. Remote Sensing, 2013, 6(2), 427–439; doi:10.1109/jstars.2013.2252601.

  • Sahoo, S. S. et al., Hyperspectral remote sensing of agriculture. Curr. Sci., 2015, 108(5), 848–859.

  • Nagaraja, S. et al., Spectral discrimination of healthy and malformed mango panicles using spectroradiometer. Indian J. Hortic., 2014, 72(1), 40–44.

  • Lehmann, J. et al., Field spectroscopy in the VNIR–SWIR region to discriminate between Mediterranean native plants and exoticinvasive shrubs based on leaf tannin content. Remote Sensing, 2015, 7(2), 1225–1241; doi:10.3390/rs70201225.

  • Pal, M. and Foody, G. M., Feature selection for classification of hyperspectral data by SVM. IEEE Trans. Geosci. Remote Sensing, 2010, 48(5), 2297–2307; doi:10.1109/tgrs.2009.2039484.

  • Ray, J. P., Use of hyperspectral remote sensing data for crop stress detection: ground-based studies. Int. Arch. Photogramm., Remote Sensing Spat. Inf. Sci., 2010, 38(8), 562–570.

  • Erudel, T. et al., Criteria comparison for classifying Peatland vegetation types using in situ hyperspectral measurements. Remote Sensing, 2017, 9(7), 748; doi:10.3390/rs9070748.

  • Diago, M. P., Fernandes, A. M., Millan, B., Tardaguila, J. and MeloPinto, P., Identification of grapevine varieties using leaf spectroscopy and partial least squares. Comput. Electron. Agric., 2013, 99, 7–13; doi:10.1016/j.compag.2013.08.021.

  • Zapolska, A. et al., Linear discriminant analysis of spectral measurements for discrimination between healthy and diseased trees of Olea europaea L. artificially infected by Fomitiporia mediterranea. Int. J. Remote Sensing, 2020, 41(14), 5388–5398; doi:10.1080/01431161.2020.1731931.

  • Shafri, H. Z. M. et al., Spectral discrimination of healthy and ganoderma-infected oil palms from hyperspectral data. Int. J. Remote Sensing, 2011, 32(22), 7111–7129; doi:10.1080/01431161.2010.519003.

  • Adam, E. et al., Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review. Wetlands Ecol. Manage., 2009, 18(3), 281–296; doi:10.1007/s11273-009-9169-z.

  • Wang, L., Li, J., Qin, H., Xu, J., Zhang, X. and Huang, L., Selecting near-infrared hyperspectral wavelengths based on one-way ANOVA to identify the origin of Lycium barbarum. In International Conference on High Performance Big Data and Intelligent Systems, Shenzhen, China, 2019, pp. 122–125.

  • Kumar, A. et al., Field hyperspectral data analysis for discriminating spectral behavior of tea plantations under various management practices. Int. J. Appl. Earth Obs. Geoinf., 2013, 23, 352–359; doi:10.1016/j.jag.2012.10.006.

  • Manjunath, K. R. et al., Discrimination of spectrally-close crops using ground-based hyperspectral data. J. Indian Soc. Remote Sensing, 2011, 39(4), 599–602; doi:10.1007/s12524-011-0099-x.

  • Huang, W. et al., New optimized spectral indices for identifying and monitoring winter wheat diseases. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sensing, 2014, 7(6), 2516–2524; doi:10.1109/jstars.2013.2294961

  • Mountrakis, G. et al., Support vector machines in remote sensing: a review. ISPRS J. Photogramm. Remote Sensing, 2011, 66(3), 247–259; doi:10.1016/j.isprsjprs.2010.11.001.

  • Lin, X. et al., Selecting feature subsets based on SVM-RFE and the overlapping ratio with applications in bioinformatics. Molecules, 2017, 23(1), 52; doi:10.3390/molecules23010052.

  • Huang, L. et al., Identification of Fusarium head blight in winter wheat ears based on Fisher’s linear discriminant analysis and a support vector machine. Appl. Sci., 2019, 9(18), 3894; doi:10.3390/app9183894.

  • https://www.malvernpanalytical.com/en/products/product-range/asd-range/fieldspec-range/fieldspec4-hi-res-high-resolution-spectroradiometer

  • Hall, M. and Smith, L. A., Feature selection for machine learning: comparing a correlation-based filter approach to the wrapper. In Florida Artificial Intelligence Research Society Conference, 1999.

  • Robnik-Šikonja, M. and Kononenko, I., Theoretical and empirical analysis of ReliefF and RReliefF. Mach. Learn., 2003, 53(1), 23– 69.

  • Curran, P. J. et al., Exploring the relationship between reflectance red edge and chlorophyll concentration in slash pine leaves. Tree Physiol., 1995, 15(3), 203–206; doi:10.1093/treephys/15.3.203.

  • Kollenkark, J. C. et al., Effects of cultural practices on agronomic and reflectance characteristics of soybean canopies 1. Agron. J., 1982, 74(4), 751–758; doi:10.2134/agronj1982.00021962007400040035x.

  • Slaton, M. R. et al., Estimating near-infrared leaf reflectance from leaf structural characteristics. Am. J. Bot., 2001, 88(2), 278–284; doi:10.2307/2657019.


Abstract Views: 279

PDF Views: 123




  • Wavelength Selection and Classification of Hyperspectral Non-Imagery Data to Discriminate Healthy and Unhealthy Vegetable Leaves

Abstract Views: 279  |  PDF Views: 123

Authors

Anjana N. Ghule
Department of Information Technology, Government College of Engineering, Aurangabad 431 005, India
Ratnadeep R. Deshmukh
Department of Computer Science and Information Technology, Dr B.A.M. University, Aurangabad 431 005, India

Abstract


Being the largest vegetarian population across the globe, vegetables are an integral part of Indian meals. The proposed research finds significant wavelengths to discriminate healthy and unhealthy vegetable plants. Spectral-reflectance (SR) and first-derivative (FD) in the visible, red edge and near infrared region (350–1000 nm) of three vegetables brinjal, cluster beans and long beans were used. The significant wavelengths were selected using ReliefF and Support- Vector-Machine (SVM). Random forest algorithm was used for classification. The binary classification was used for each vegetable separately, and multiclass classification was applied for all the samples. The most significant spectral wavelengths, for the prediction of diseased brinjal, correspond primarily to the red edge in SR. Long beans samples were classified accurately in the red-edge. In the case of cluster beans, SR is more effective than FD in the red-edge. The results substantiate the utility of HS data for discrimination of healthy and unhealthy vegetable plants and even vegetable types.

Keywords


Classification Accuracy, Healthy and Unhealthy Vegetable Plants, Hyperspectral Measurements, Spectral Reflectance, Wavelength Selection.

References





DOI: https://doi.org/10.18520/cs%2Fv120%2Fi5%2F936-941