Detecting and Severity Measurement of Downy Mildew Disease in Greenhouse Cucumber Leaves Using Image Processing Technique

Downy Mildew of cucurbits is one of the most important diseases of cucumber in humid areas and greenhouses. It can lead to significant damages to the quality and quantity of the product, if not diagnosed on time. In this study, the possibility of using image processing for determining the downy mildew of greenhouse cucumber was investigated. The captured images from cucumber leaves at several stages of disease severity were processed in Image Processing toolbox of MATLAB programming software. Color images were transferred to several color spaces and then color components were examined by discriminant analysis. Cr color component was determined to be suitable to detect disease spots in leaf and was used to develop the recognition algorithm. The accuracy of algorithm in terms of identify the infected areas of leaves was 97.4±1.4 percent. Discriminant analysis was also used to classify the severity of the disease. Results revealed that image processing is a suitable method for accurate diagnosis of downy mildew in greenhouse cucumber leaves. Discriminant analysis is also a useful tool to classify disease severity in images resulted from image processing.