The paper presents an image processing method for the quantitative assessment of ROS accumulation areas in leaves stained with DAB or NBT for H2O2 and O2- detection, respectively. Three types of images determined by the combination of staining method and background color are considered. The method is based on the principle of supervised machine learning with manually labeled image patterns used for training. The method's algorithm is developed as a JavaScript macro in the public domain Fiji (ImageJ) environment. It allows to select the stained regions of ROS-mediated histochemical reactions, subsequently fractionated according to the weak, medium and intense staining intensity and thus ROS accumulation. It also evaluates total leaf blade area. The precision of ROS accumulation area detection is validated by the Dice Similarity Coefficient in the case of manual patterns. The proposed framework reduces the computation complexity, once prepared, requires less image processing expertise than the competitive methods and represents a routine quantitative imaging assay for a general histochemical image classification.
Keywords: Histochemical ROS detection; Hydrogen peroxide; Image segmentation; ImageJ; Superoxide anion radical; Weka classifier.
Copyright © 2016 Elsevier Inc. All rights reserved.