Segmenting High-quality Digital Images of Stomata using the Wavelet Spot Detection and the Watershed Transform

Duarte, Kauê T. N.; Carvalho, Marco António Garcia de; Martins, Paulo S.

doi:10.5220/0006168105400547

Cited by 17 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, previous methods have not been widely adopted by the community and many researchers are likely to manually count stomata. Previous methods relied on substantial image pre-processing to generate images for thresholding to isolate stomata for counting (Oliviera et al, 2014;Duarte et al, 2017). Thresholding can perform well in a homogenous collection of images, but quickly fails when images collected by different preparation and micrscopy methods are provided to the thresholding method (K. Fetter, pers.…”

Section: Discussionmentioning

confidence: 99%

“…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.…”

mentioning

confidence: 99%

See 1 more Smart Citation

StomataCounter: a neural network for automatic stomata identification and counting

Fetter

Eberhardt

Barclay

et al. 2018

Preprint

View full text Add to dashboard Cite

Stomata regulate important physiological processes in plants and are often phenotyped by researchers in diverse fields of plant biology. Currently, there are no user friendly, fully-automated methods to perform the task of identifying and counting stomata, and stomata density is generally estimated by manually counting stomata.• We introduce StomataCounter, an automated stomata counting system using a deep convolutional neural network to identify stomata in a variety of different microscopic images. We use a humanin-the-loop approach to train and refine a neural network on a taxonomically diverse collection of microscopic images.• Our network achieves 98.1% identification accuracy on Ginkgo SEM micrographs, and 94.2% transfer accuracy when tested on untrained species.• To facilitate adoption of the method, we provide the method in a publicly available website at http: //www.stomata.science/.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

StomataCounter: a neural network for automatic stomata identification and counting

Fetter

Eberhardt

Barclay

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…al. [21] proposed a method to automatically count stomata in microscope images. Initially, the images were converted from RGB to CieLAB in order to select the best channel for analysis.…”

Section: Related Workmentioning

confidence: 99%

A Stomata Classification and Detection System in Microscope Images of Maize Cultivars

Aono

Nagai

Dickel

et al. 2019

Preprint

View full text Add to dashboard Cite

Stomata are morphological structures of plants that have been receiving constant attention. These pores are responsible for the interaction between the internal plant system and the environment, working on different processes such as photosynthesis process and transpiration stream. As evaluated before, understanding the pore mechanism play a key role to explore the evolution and behavior of plants. Although the study of stomata in dicots species of plants have advanced, there is little information about stomata of cereal grasses. In addition, automated detection of these structures have been presented on the literature, but some gaps are still uncovered. This fact is motivated by high morphological variation of stomata and the presence of noise from the image acquisition step. Herein, we propose a new methodology of an automatic stomata classification and detection system in microscope images for maize cultivars.In our experiments, we have achieved an approximated accuracy of 97.1% in the identification of stomata regions using classifiers based on deep learning features. 1According to Willmer and Fricker [1], from all points of view, the stomata have received more 2 constant attention probably than any other single vegetative structure in the plant. Regulating 3 gas exchange between the plant and the environment[2], these structures are small pores on the 4 surfaces of leaves, stems and parts of angiosperm flowers and fruits [3, 4], formed by a pair of 5 specialized epidermal cells (guarder cells), which are found in the surface of aerial parts of most 6 higher plants [1]. Due to the controlling of the exchange of water vapour and CO 2 between the 7 interior of the leaf and the atmosphere [3]; the photosynthesis, the transpiration stream, the 8 nutrition and the metabolism of land plants are in different ways related to the opening and 9 closing movements of the stomata [4, 1]. Furthermore, Hetherington and Woodward point that 10 the acquisition of stomata and an impervious leaf cuticle are considered to be key elements in 11 the evolution of advanced terrestrial plants, allowing the plant to inhabit a range of different, 12 often fluctuating environments but still control water content [3].13 The stomatal movements distinguish this structure from other pores found in plant organs, of liverworts [1]. The control of stomatal aperture requires the coordinated control of multiple 16 cellular processes [3] and its morphogenesis is affected by several environmental stimuli, such 17 as relative humidity, temperature, concentration of atmospheric carbon dioxide, light intensity, 18 and endogenous plant hormones [2, 3, 1]. Global warming for example could increase leaf 19 transpiration and soil evaporation, and as consequence leaf stomata movements can control 20 plant water loss and carbon gain under this water stress condition [5]. Stomatal aperture 21 might also represent an initial response to both plants and human pathogenic bacteria [2]. In 22 plants, it has been reported that microscopic surface openings serve as...

show abstract

“…Scarlett, Tang, Petrie, and Whitty (2016) for instance, apply maximum stable external regions to detect potential ellipses of stomata on microscope images of vine leaves while da Silva Oliveira et al 2014use Gaussian filtering and a series of morphological operations to detect stomata on optical microscope imagery of five different plant species. Duarte et al (2017) use wavelet spot detection in tandem with standard image processing tools to segment stomata on one plant species, and Higaki et al By training a Haar feature-based classifier with exemplary stomata, they can be detected with high accuracy on SEM microphotographs. Jayakody, Liu, Whitty, and Petrie (2017) use a cascade object detection learning algorithm to correctly identify multiple stomata on rather large microscopic images of grapevine leaves, but also apply a combination of image processing techniques to estimate the pore dimensions of the stomata that were detected with the cascade object detector.…”

Section: Introductionmentioning

confidence: 99%

From leaf to label: A robust automated workflow for stomata detection

Meeus

Bulcke

wyffels

2020

Ecology and Evolution

View full text Add to dashboard Cite

Plant leaf stomata are the gatekeepers of the atmosphere–plant interface and are essential building blocks of land surface models as they control transpiration and photosynthesis. Although more stomatal trait data are needed to significantly reduce the error in these model predictions, recording these traits is time‐consuming, and no standardized protocol is currently available. Some attempts were made to automate stomatal detection from photomicrographs; however, these approaches have the disadvantage of using classic image processing or targeting a narrow taxonomic entity which makes these technologies less robust and generalizable to other plant species. We propose an easy‐to‐use and adaptable workflow from leaf to label. A methodology for automatic stomata detection was developed using deep neural networks according to the state of the art and its applicability demonstrated across the phylogeny of the angiosperms. We used a patch‐based approach for training/tuning three different deep learning architectures. For training, we used 431 micrographs taken from leaf prints made according to the nail polish method from herbarium specimens of 19 species. The best‐performing architecture was tested on 595 images of 16 additional species spread across the angiosperm phylogeny. The nail polish method was successfully applied in 78% of the species sampled here. The VGG19 architecture slightly outperformed the basic shallow and deep architectures, with a confidence threshold equal to 0.7 resulting in an optimal trade‐off between precision and recall. Applying this threshold, the VGG19 architecture obtained an average F‐score of 0.87, 0.89, and 0.67 on the training, validation, and unseen test set, respectively. The average accuracy was very high (94%) for computed stomatal counts on unseen images of species used for training. The leaf‐to‐label pipeline is an easy‐to‐use workflow for researchers of different areas of expertise interested in detecting stomata more efficiently. The described methodology was based on multiple species and well‐established methods so that it can serve as a reference for future work.

show abstract

Segmenting High-quality Digital Images of Stomata using the Wavelet Spot Detection and the Watershed Transform

Cited by 17 publications

References 0 publications

StomataCounter: a neural network for automatic stomata identification and counting

StomataCounter: a neural network for automatic stomata identification and counting

A Stomata Classification and Detection System in Microscope Images of Maize Cultivars

From leaf to label: A robust automated workflow for stomata detection

Contact Info

Product

Resources

About