Microscope image based fully automated stomata detection and pore measurement method for grapevines

Abstract

BackgroundStomatal behavior in grapevines has been identified as a good indicator of the water stress level and overall health of the plant. Microscope images are often used to analyze stomatal behavior in plants. However, most of the current approaches involve manual measurement of stomatal features. The main aim of this research is to develop a fully automated stomata detection and pore measurement method for grapevines, taking microscope images as the input. The proposed approach, which employs machine learning and image processing techniques, can outperform available manual and semi-automatic methods used to identify and estimate stomatal morphological features.ResultsFirst, a cascade object detection learning algorithm is developed to correctly identify multiple stomata in a large microscopic image. Once the regions of interest which contain stomata are identified and extracted, a combination of image processing techniques are applied to estimate the pore dimensions of the stomata. The stomata detection approach was compared with an existing fully automated template matching technique and a semi-automatic maximum stable extremal regions approach, with the proposed method clearly surpassing the performance of the existing techniques with a precision of 91.68% and an F1-score of 0.85. Next, the morphological features of the detected stomata were measured. Contrary to existing approaches, the proposed image segmentation and skeletonization method allows us to estimate the pore dimensions even in cases where the stomatal pore boundary is only partially visible in the microscope image. A test conducted using 1267 images of stomata showed that the segmentation and skeletonization approach was able to correctly identify the stoma opening 86.27% of the time. Further comparisons made with manually traced stoma openings indicated that the proposed method is able to estimate stomata morphological features with accuracies of 89.03% for area, 94.06% for major axis length, 93.31% for minor axis length and 99.43% for eccentricity.ConclusionsThe proposed fully automated solution for stomata detection and measurement is able to produce results far superior to existing automatic and semi-automatic methods. This method not only produces a low number of false positives in the stomata detection stage, it can also accurately estimate the pore dimensions of partially incomplete stomata images. In addition, it can process thousands of stomata in minutes, eliminating the need for researchers to manually measure stomata, thereby accelerating the process of analysing plant health.

The use of quantitative imaging to investigate regulators of membrane trafficking in Arabidopsis stomatal closure

“…Light microscopy is a powerful tool to investigate stomatal behaviours . Combined with quantitative image and data analysis, it has vastly expanded the potential for genetic screening . To automate measurements of stomatal pores, we used an image analysis framework for high‐content screening and developed the StomataMeasurer tool that performs both stomatal pore object detection combined with quantification.…”

“…15,16 Combined with quantitative image and data analysis, it has vastly expanded the potential for genetic screening. 9,38 To automate measurements of stomatal pores, we used an image analysis framework for high-content screening and developed the StomataMeasurer tool that performs both stomatal pore object detection combined with quantification. For stomatal pore detection, we imaged autofluorescence signals present at the stomatal lip followed by detection of the inner pore ( Figure 1).…”

StomataCounter: a neural network for automatic stomata identification and counting

“…These methods invariably requires the user to participate in the counting process to tune parameters and monitor the image processing, and are not fully autonomous. More recently, cascade classifier methods have been developed which perform well on small collections of test sets (Vialet-Chabrand and Brendel, 2014;Jayakody et al, 2017). Additionally, most methods rely on a very small set of images (50 to 500) typically sampled from just a few species to create the training and/or test set.…”

“…Here, we seek to minimize the burden of high-throughput phenotyping of stomatal traits by introducing an automated method to recognize and count stomata from plant epidermal micrographs. Although automated methods using computer vision have been suggested (Higaki et al, 2014;Laga et al, 2014;Duarte et al, 2017;Jayakody et al, 2017), these highly specialized approaches require feature engineering specific to an image class. Such features typically transfer poorly to images from a new source, such as images recorded using different microscopy and illumination techniques, or different image processing protocols.…”

In-situ Real-time Field Imaging and Monitoring of Leaf Stomata by High-resolution Portable Microscope

“…[9][10][11][12]. On the other hand, direct measurement mainly utilizes microscopic images of a detached leaf or imprints of an intact leaf, which often requires invasive manipulations (physical or chemical) of a leaf [13][14][15]. Optical microscopy of abaxial stomata of an intact leaf by a conventional reflected microscope requires 180 degrees folding of a leaf to face the abaxial side towards the objective lens.…”