Comparison of visible-near infrared and mid-infrared spectroscopy for classification of Huanglongbing and citrus canker infected leaves


  • Sindhuja Sankaran University of Florida
  • Reza Ehsani Citrus Research and Education Center


Disease detection, classification, quadratic discriminant analysis, k-nearest neighbor, USA.


In this study, visible-near infrared spectroscopy and mid-infrared spectroscopy were compared to evaluate their applicability in classifying citrus leaves infected with canker and HLB from healthy citrus leaves.  The visible-near infrared spectra in the range 350-2,500 nm and mid-infrared spectra in the range of 5.15-10.72 µm were collected from healthy and diseased (canker, HLB) leaves.  Following the spectral data collection, the data were preprocessed and classification was performed using two classifiers, quadratic discriminant analysis (QDA) and k-nearest neighbor (kNN).  The classifiers (QDA, kNN) resulted in an average overall and individual class classification accuracy of about 90% or more.  Mid-infrared spectroscopy provided high classification accuracy especially in identifying HLB-infected leaves; while, visible-near infrared spectroscopy was better suited for canker detection.  Both methods have their own merits such as visible-near infrared spectroscopy offers non-invasive disease detection; while mid-infrared spectroscopy represents the chemical profile of the leaf structure, which may allow potential detection in asymptomatic stages.


Keywords: disease detection, classification, quadratic discriminant analysis, k-nearest neighbor

Author Biographies

Sindhuja Sankaran, University of Florida

Postdoc with Reza Ehsani, published good review paper on sensing disease---JKSchueller feb11

Reza Ehsani, Citrus Research and Education Center

Associate Professor






III-Equipment Engineering for Plant Production