Alireza Pourreza

An optimum method for real-time in-field detection of Huanglongbing disease using a vision sensor

Starch in HLB infected leaf rotates the polarization plane of light.HLB infection was accurately identified by the customized vision sensor.Vision sensor can identify HLB infection on-the-go.Vision sensor was developed using inexpensive components. Huanglongbing (HLB) or citrus greening is a bacterial infection which is spread by a citrus psyllid. No effective cure for this disease has been reported yet, and the HLB-infected tree will eventually die. Therefore, the infected tree must be detected and removed immediately to stop the spread of the disease. One of the symptoms of HLB is the accumulation of starch which creates blotchy mottles in an asymmetrical pattern on infected citrus leaves. These blotchy mottles symptoms may be confused with the deficiency of certain nutrients such as zinc or magnesium. We showed in a previous study that the unique capability of starch to rotate the polarization planar of light can be employed to identify the HLB-infected citrus leaves and differentiate them from zinc or magnesium deficiency. In this study, a vision sensor was developed for the purpose of real-time HLB detection for use under field conditions. The sensor included a highly sensitive monochrome camera, narrow band high power LEDs, and polarizing filters. The sensor was first tested and calibrated in a simulated field condition in a laboratory. Then, it was tested in a citrus grove. Two simple image descriptors; mean and standard deviation of gray values, were used for the purpose of classification. The results showed that the sensor clearly highlighted the starch accumulation in the HLB-infected leaf and differentiated it from visually analogous symptoms of zinc deficiency. HLB detection accuracies which ranged from 95.5% to 98.5% were achieved during the laboratory and field experiments.

Feasibility of Using the Optical Sensing Techniques for Early Detection of Huanglongbing in Citrus Seedlings

A vision sensor was introduced and tested for early detection of citrus Huanglongbing (HLB). This disease is caused by the bacterium Candidatus Liberibacter asiaticus (CLas) and is transmitted by the Asian citrus psyllid. HLB is a devastating disease that has exerted a significant impact on citrus yield and quality in Florida. Unfortunately, no cure has been reported for HLB. Starch accumulates in HLB infected leaf chloroplasts, which causes the mottled blotchy green pattern. Starch rotates the polarization plane of light. A polarized imaging technique was used to detect the polarization-rotation caused by the hyper-accumulation of starch as a pre-symptomatic indication of HLB in young seedlings. Citrus seedlings were grown in a room with controlled conditions and exposed to intensive feeding by CLas-positive psyllids for eight weeks. A quantitative polymerase chain reaction was employed to confirm the HLB status of samples. Two datasets were acquired; the first created one month after the exposer to psyllids and the second two months later. The results showed that, with relatively unsophisticated imaging equipment, four levels of HLB infections could be detected with accuracies of 72%–81%. As expected, increasing the time interval between psyllid exposure and imaging increased the development of symptoms and, accordingly, improved the detection accuracy.

An automatic foreign materials detection of barberries using red-free image processing

In this study, a new approach is introduced for automatically detecting of visual foreign materials like peduncles, leaves and blight products in mass of Barberries. The segmentation algorithm has been developed for red-free images of barberries. Cr plane of YCbCr color space is used to detect the target area of images. Because of shining of barberrys glossy cortex during imaging, there are many pixels with the same color of the target areas in Cr plane. A simple equation using statistic parameters of binary images is used to find a compatible threshold for detecting the target areas in each image. With this algorithm, the foreign materials are acceptably detected compared to manually segmented images. This method is very useful when there are many unwanted partially big regions in the image with the same color of target areas.