Citrus Huanglongbing Detection Using Narrow-Band Imaging and Polarized Illumination
Huanglongbing (HLB) or Citrus Greening
The insect-spread bacterial infection known as citrus greening or Huanglongbing (HLB) is a very destructive citrus disease and has caused massive losses in Florida’s citrus industry. Early, easy, and less expensive HLB detection based on particular symptoms, such as starch accumulation in the citrus leaf, would increase the chance of preventing the disease from being spread and causing more damage.
The leaf samples were collected from the ‘Hamlin’ and ‘Valencia’ varieties of citrus. Three classes of samples (magnesium-deficient, HLB-positive zinc-deficient, and HLB-negative zinc-deficient) were considered in the classification process to confirm the starch detection ability of the system.
Preliminary Experiment
In order to evaluate the effect of starch accumulation in HLB-symptomatic leaves on the polarization planar of the light, an initial experiment was conducted in May 2010 in the Citrus Research and Education Center (CREC) in Lake Alfred, Florida. In this experiment, citrus canopies were illuminated (after sunset in darkness) with a halogen lamp (100 W, JCD type, GY 6.35) and a polarized filter mounted in front of the lamp. Leaf reflectance was measured using a portable spectrometer (HR-1024, Spectra Vista Corp., Poughkeepsie, N.Y.) with another polarized filter installed in front of the spectrometer in two separate positions: parallel to the lamp filter (to measure the maximum reflectance) and perpendicular to the lamp filter (to measure the minimum reflectance).
Figure above shows maximum and minimum reflectance using parallel and perpendicular filters, respectively. The spectra are averages of ten different sample measurements, and their standard deviations are shown as error bars at each wavelength. Part c is the minimum to maximum reflectance ratio of control (healthy) and greening (HLB-symptomatic) samples. The ratio of the healthy and symptomatic leaf reflectance ratios is plotted in part d. As shown in this figure, the highest ratio (1.6) was found near 600 nm, which suggests that this is the optimal wavelength for detecting HLB-symptomatic leaves. In addition, the ratio was close to 1.0 at 400 nm, which means that the min/max ratio of healthy and HLB-symptomatic leaves is the same, so this wavelength can be used as a reference wavelength.
Image Acquisition System
The ability of narrow-band imaging and polarizing filters in detecting starch accumulation in symptomatic citrus leaf was evaluated in this study. A custom-made image acquisition system was developed for this purpose in which leaf samples were illuminated with polarized light using narrow-band high-power LEDs at 400 nm and 591 nm, and the reflectance was measured by two monochrome cameras. Two polarizing filters were mounted in perpendicular directions in front of the cameras so that each camera acquired an image with reflected light in only one direction (parallel or perpendicular to the illumination polarization).
Four groups of textural features, including gray, local binary pattern, local similarity pattern, and gray-level co-occurrence features, were extracted and ranked using several feature selection methods. Seven classifiers (support vector machine, linear, naive Bayes linear, quadratic, naive Bayes quadratic, Mahalanobis, and k nearest neighbor) were evaluated, and the best classifiers and sets of features were selected based on their accuracy.
Overall average accuracies of 93.1% and 89.6% in HLB detection were obtained for the ‘Hamlin’ and ‘Valencia’ varieties, respectively, using a step-by-step classification method. The results of this study showed that the starch accumulation in HLB-symptomatic leaves rotated the polarization planar of light at 591 nm, and this property can be effectively used in a fast and inexpensive HLB detection system.