Browsing by Subject "fire blight"

Now showing 1 - 1 of 1

Access status: Open Access ,
An algorithm to extract first and second order venation of apple-tree leaves stained for H2O2 detection
(Wydawnictwa AGH, 2010) Sekulska-Nalewajko, Joanna; Gocławski, Jarosław; Gajewska, Ewa Grażyna; Wielanek, Marzena Katarzyna
In the paper an algorithm for the extraction of first and second order leaf venation has been presented. The algorithm applies to apple tree leaves specially stained to reveal the areas of $H_{2}O_{2}$ appearing in the leaf blade as brown spots of different size and intensity. In the considered case they represent the defence reaction of planfs tissue to a bacterial infection called fire blight. Examined leaf images include visible leaf veins with colour hue and brightness similar to the $H_{2}O_{2}$ spots. They are often superimposed on leaf veins and make serious distortions for the process of their extraction. In these conditions typical algorithms for the detection of venation patterns usually fail, so a new method of primary and secondary veins detection has been proposed. The vein extraction is based on the step-wise tracking of each vein axis using polygonal linę with the line segments of fixed size. The optimal direction for each step is obtained through the minimization of the proposed cost function depending on the prediction angle. The algorithm has been written in the M-language and executed in MATLAB environment. The experiments of leaf vein tracking carried out for the series of images gave promising results accepted by the biologists.