An image segmentation technique with statistical strategies for pesticide efficacy assessment

Abstract

Image analysis is a useful technique to evaluate the efficacy of a treatment for weed control. In this study, we address two practical challenges in the image analysis. First, it is challenging to accurately quantify the efficacy of a treatment when an entire experimental unit is not affected by the treatment. Second, RGB codes, which can be used to identify weed growth in the image analysis, may not be stable due to various surrounding factors, human errors, and unknown reasons. To address the former challenge, the technique of image segmentation is considered. To address the latter challenge, the proportion of weed area is adjusted under a beta regression model. The beta regression is a useful statistical method when the outcome variable (proportion) ranges between zero and one. In this study, we attempt to accurately evaluate the efficacy of a 35% hydrogen peroxide (HP). The image segmentation was applied to separate two zones, where the HP was directly applied (gray zone) and its surroundings (nongray zone). The weed growth was monitored for five days after the treatment, and the beta regression was implemented to compare the weed growth between the gray zone and the control group and between the nongray zone and the control group. The estimated treatment effect was substantially different after the implementation of image segmentation and the adjustment of green area.