Author
BOCK, C.H. - University Of Florida | |
PARKER, P.E. - Animal And Plant Health Inspection Service (APHIS) | |
COOK, A.Z. - Animal And Plant Health Inspection Service (APHIS) | |
Gottwald, Timothy |
Submitted to: Plant Disease
Publication Type: Peer Reviewed Journal Publication Acceptance Date: 3/6/2009 Publication Date: 6/1/2009 Citation: Bock, C., Parker, P., Cook, A., Gottwald, T.R. 2009. Automated image analysis of the severity of foliar citrus canker symptoms. Plant Disease. 93:660-665 Interpretive Summary: Citrus canker (caused by Xanthomonas citri subsp. citri) causes severe damage to citrus crops, reducing yield, and rendering fruit unfit for fresh sale. Disease assessment is needed for many purposes, including basing decisions and monitoring epidemics. However, disease severity estimates by raters are known to be particularly error prone. To better assess disease and ensure that sevrity data are precise and accurate measures or estimates of disease, image analysis was investigated as a tool for assessing disease. The study compared measurements of citrus canker severity (percent area infected) from automated image analysis to visual estimates by raters and true values using images from leaf samples. Severity on leaves was measured by automated image analysis using different methods, and the results showed that healthy leaf area color replacement gave the most consistent agreement with the true severity data. No one rater or method was best for every leaf sample, but replacing healthy color in each leaf with a standard color before automation of image analysis improved agreement, and was relatively quick (20 sec. per image). The accuracy and precision of automated image analysis of citrus canker severity can be comparable to unaided, direct visual estimation by average raters. Technical Abstract: Citrus canker (caused by Xanthomonas citri subsp. citri) is a destructive disease, reducing yield, and rendering fruit unfit for fresh sale. Accurate assessment of citrus canker severity and other diseases is needed for several purposes, including monitoring epidemics and evaluation of germplasm. We compared measurements of citrus canker severity (percent area infected) from automated image analysis to visual estimates by raters and true values using images from five leaf samples (65, 123, 50, 50 and 200 leaves; disease severity from 0 to 60%). Severity on leaves was measured by automated image analysis by i) basing threshold values on a presample of leaves, or ii) replacing healthy leaf color on a leaf-by-leaf basis before automating image analysis. Samples 1-4 were assessed by three trained plant pathologists, and sample 5 was assessed by an additional 25 raters. Healthy leaf area color replacement gave the most consistent agreement with the true severity data. Using color replacement, agreement with true values based on Lin’s concordance correlation coefficient ('c) was 0.93, 0.79, 0.71, 0.85, and 0.89 for each of the samples, respectively. The range and consistency of agreement was generally less good for automated thresholds based on a presample ('c=0.35-0.90) or visual raters ('c=0.30-0.94). The constituents of agreement (precision and accuracy) showed similar trends. No one rater or method was best for every leaf sample, but replacing healthy color in each leaf with a standard color before automation of image analysis improved agreement, and was relatively quick (20 sec. per image). The accuracy and precision of automated image analysis of citrus canker severity can be comparable to unaided, direct visual estimation by many raters. |