Detection of Gray Mold Infection in Plants Using a Multispectral Imaging System

Abstract

Gray mold disease caused by the fungus Botrytis cinerea damages many crop hosts worldwide 9and is responsible for heavy economic losses. Early diagnosis and detection of the disease would allow 10 for more effective crop management practices to prevent outbreaks in field or greenhouse settings. 11Furthermore, having a simple, non-invasive way to quantify the extent of gray mold disease is important 12for plant pathologists interested in quantifying infection rates. In this paper, we design and build a 13 multispectral imaging system for discriminating between leaf regions, infected with gray mold, and those 14 that remain unharmed on a lettuce (Lactuca spp.) host. First, we describe a method to select two optimal 15(high contrast) spectral bands from continuous hyperspectral imagery (450-800 nm). We then built a 16 system based on these two spectral bands, located at 540 and 670 nm. The resultant system uses two 17 cameras, with a narrow band-pass spectral filter mounted on each, to measure the multispectral 18 reflectance of a lettuce leaf. The two resulting images are combined using a normalized difference 19 calculation that produces a single image with high contrast between the leaves' infected and healthy 20 regions. A classifier was then created based on the thresholding of single pixel values. We demonstrate 21 that this simple classification produces a true positive rate of 95.25% with a false positive rate of 9.316%. 22 23

Determination of Specific Parameters for Early Detection of Botrytis cinerea in Lettuce

“…Generally, the early detection of the B. cinerea infection in horticultural crops using nondestructive methods is an emerging topic. Such an evaluation method requires considering the relative position between the leaf and detector and the lighting conditions [3]. The study of Wu et al [24] showed 85% accuracy before infection symptoms were visible in eggplant leaves when the hyperspectral visible near-infrared (VNIR) spectroradiometer to measure reflectance intensities of healthy and B. cinerea inoculated plants was used.…”

“…In another study, the 552 nm and 701 nm wavelengths for detecting discolouration in lettuce leaves with over 99% accuracy were approved, but not for Botrytis fungal infection [25]. Scarboro et al demonstrated a process for selecting optimal spectral bands integrated into a two-band multispectral (540 and 670 nm) camera imaging system and evaluating its performance for detecting B. cinerea infection on lettuce leaves to monitor disease progression producing a true positive rate of 95.25% with a false positive rate of 9.316% [3]. Such findings, as mentioned earlier, can be considered for choosing leaf spectral reflectance indices according to the wavelengths used in the formulas of their calculation.…”

“…The grey mould caused by Botrytis cinerea damages many crop hosts (over 200 species) worldwide [2,3]. This fungus mainly enters the plant via direct penetration or natural openings or wounds [4,5].…”

“…Furthermore, fungal infections can alter leaf morphology and light reflectance, distinguished using leaf spectral indices [11]. Again, having a rapid, simple, non-invasive way to detect the extent of Botrytis disease is essential for plant pathologists interested in quantifying infection rates [3].…”