Automatic segmentation and measurement methods of living stomata of plants based on the CV model.

Abstract

Background The stomata of plants mainly regulate gas exchange and water dispersion between the interior and external environments of plants and play a major role in the plants' health. The existing methods of stomata segmentation and measurement are mostly for specialized plants. The purpose of this research is to develop a generic method for the fully automated segmentation and measurement of the living stomata of different plants. The proposed method utilizes level set theory and image processing technology and can outperform the existing stomata segmentation and measurement methods based on threshold and skeleton in terms of its versatility. Results The single stomata images of different plants were the input of the method and a level set based on the Chan-Vese model was used for stomatal segmentation. This allowed the morphological features of the stomata to be measured. Contrary to existing methods, the proposed segmentation method does not need any prior information about the stomata and is independent of the plant types. The segmentation results of 692 living stomata of black poplars show that the average measurement accuracies of the major and minor axes, area, eccentricity and opening degree are 95.68%, 95.53%, 93.04%, 99.46% and 94.32%, respectively. A segmentation test on dayflower ( Commelina benghalensis ) stomata data available in the literature was completed. The results show that the proposed method can effectively segment the stomata images (181 stomata) of dayflowers using bright-field microscopy. The fitted slope of the manually and automatically measured aperture is 0.993, and the R 2 value is 0.9828, which slightly outperforms the segmentation results that are given in the literature. Conclusions The proposed automated segmentation and measurement method for living stomata is superior to the existing methods based on the threshold and skeletonization in terms of versatility. The method does not need any prior information about the stomata. It is an unconstrained segmentation method, which can accurately segment and measure the stomata for different types of plants (woody or herbs). The method can automatically discriminate whether the pore region is independent or not and perform pore region extraction. In addition, the segmentation accuracy of the method is positively correlated with the stomata's opening degree.

Plant phenotyping relevance

植物の気孔画像から形態形質と開口度を自動抽出する汎用セグメンテーション・測定法を開発し、複数植物種で精度検証しており、表現型取得手法が研究の中心である。

Code and data availability

The paper's stomata image datasets and source code are only available from the corresponding author on reasonable request; the cited GitHub link is the generic third-party Faster-RCNN implementation, not a paper-specific asset.

No evidence-backed public reproduction asset is currently recorded.