Abstract :
This work describes a dedicated software which detects
and characterizes disease lesions on leaves to provide
data on the number and type of lesions and the percentage
of leaf area diseased (severity). The software, written in
Cʹ*, can be used with a standard computer in combination
with a colour CCD camera and a frame grabber
for image acquisition. The usefulness and adaptability
of the software was evaluated using two foliar diseases,
Altemaria blight of sunflower and oat leaf rust {Pmcinia
coronata f.sp. avenae], which differ in symptoms. Using
image segmentation and classification techniques, the
software discriminated disease symptoms from the healthy
leaf area. The number and size of lesions and severity,
obtained using the image processing software, were compared
with those calculated using a software planimeter
or visual assessment. Significant linear relationships
between planimeter and the imaging software were
obtained for lesion number and severity in oal leaf rust
and for severity in sunflower blight. Artefacts, mistakenly
classified as blight lesions by the imaging software
resulted in an over-estimation of the number of lesions.
Future research is aimed at improving accuracy through
better illumination during image capture. A dedicated,
compact and portable hardware is currently being
developed for field use as a self-contained device for disease
assessment
