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. 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 R2 value is 0.9828, which slightly outperforms the segmentation results that are given in the literature. 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.

Stomata are microscopic pores on the plant epidermis that regulate the water content and CO₂ levels in leaves. Thus, they play an important role in plant growth and development. Currently, most of the common methods for the measurement of pore anatomy parameters involve manual measurement or semi-automatic analysis technology, which makes it difficult to achieve high-throughput and automated processing. This paper presents a method for the automatic segmentation and parameter calculation of stomatal pores in microscope images of plant leaves based on deep convolutional neural networks. The proposed method uses a type of convolutional neural network model (Mask R-CNN (region-based convolutional neural network)) to obtain the contour coordinates of the pore regions in microscope images of leaves. The anatomy parameters of pores are then obtained by ellipse fitting technology, and the quantitative analysis of pore parameters is implemented. Stomatal microscope image datasets for black poplar leaves were obtained using a large depth-of-field microscope observation system, the VHX-2000, from Keyence Corporation. The images used in the training, validation, and test sets were taken randomly from the datasets (562, 188, and 188 images, respectively). After 10-fold cross validation, the 188 test images were found to contain an average of 2278 pores (pore widths smaller than 0.34 μm (1.65 pixels) were considered to be closed stomata), and an average of 2201 pores were detected by our network with a detection accuracy of 96.6%, and the intersection of union (IoU) of the pores was 0.82. The segmentation results of 2201 stomatal pores of black poplar leaves showed that the average measurement accuracies of the (a) pore length, (b) pore width, (c) area, (d) eccentricity, and (e) degree of stomatal opening, with a ratio of width-to-maximum length of a stomatal pore, were (a) 94.66%, (b) 93.54%, (c) 90.73%, (d) 99.09%, and (e) 92.95%, respectively. The proposed stomatal pore detection and measurement method based on the Mask R-CNN can automatically measure the anatomy parameters of pores in plants, thus helping researchers to obtain accurate stomatal pore information for leaves in an efficient and simple way.

Hand bone age, as the biological age of humans, can accurately reflect the development level and maturity of individuals. Bone age assessment results of adolescents can provide a theoretical basis for their growth and development and height prediction. In this study, a deep convolutional neural network (CNN) model based on fine-grained image classification is proposed, using a hand bone image dataset provided by the Radiological Society of North America (RSNA) as the research object. This model can automatically locate informative regions and extract local features in the process of hand bone image recognition, and then, the extracted local features are combined with global features of a complete image for bone age classification. This method can achieve end-to-end bone age assessment without any image annotation information (except bone age tags), improving the speed and accuracy of bone age assessment. Experimental results show that the proposed method achieves 66.38% and 68.63% recognition accuracy of males and females on the RSNA dataset, and the mean absolute errors are 3.71 ± 7.55 and 3.81 ± 7.74 months for males and females, respectively. The test time for each image is approximately 35 ms. This method achieves good performance and outperforms existing methods in bone age assessment based on weakly supervised fine-grained image classification.

Research Highlights: This paper proposes a new method for hemispherical forest canopy image segmentation. The method is based on a deep learning methodology and provides a robust and fully automatic technique for the segmentation of forest canopy hemispherical photography (CHP) and gap fraction (GF) calculation. Background and Objectives: CHP is widely used to estimate structural forest variables. The GF is the most important parameter for calculating the leaf area index (LAI), and its calculation requires the binary segmentation result of the CHP. Materials and Methods: Our method consists of three modules, namely, northing correction, valid region extraction, and hemispherical image segmentation. In these steps, a core procedure is hemispherical canopy image segmentation based on the U-Net convolutional neural network. Our method is compared with traditional threshold methods (e.g., the Otsu and Ridler methods), a fuzzy clustering method (FCM), commercial professional software (WinSCANOPY), and the Habitat-Net network method. Results: The experimental results show that the method presented here achieves a Dice similarity coefficient (DSC) of 89.20% and an accuracy of 98.73%. Conclusions: The method presented here outperforms the Habitat-Net and WinSCANOPY methods, along with the FCM, and it is significantly better than the Otsu and Ridler threshold methods. The method takes the original canopy hemisphere image first and then automatically executes the three modules in sequence, and finally outputs the binary segmentation map. The method presented here is a pipelined, end-to-end method.

Stomata are the main medium of water exchange in plants, regulating gas exchange and responsible for the processes of photosynthesis and transpiration. Stomata are surrounded by guard cells and the transpiration rate is controlled by opening and closing stomata. Stomatal state (open and close) plays an important role in describing the health of plants. In addition, counting the number of stomata is of great significance for scientists to study the number of opening and closeing stomata and to measure their density and distribution on the leaf surface through different sampling techniques. Although some techniques for calculating the number of stomata have been proposed, these methods are used to produce samples in isolation and then to identify and classify the states in the sample leaves. We improved YOLO-X and then implemented a transfer learning method to count the number of stomata and identify the stomatal opening and closing status of live black poplar leaves. In the end, the average accuracy and recall of the method were 98.3% and 95.9%, which helped researchers to obtain accurate information on leaf stomatal opening and closing status in an efficient and simple way.