Stomata in leaf epidermis images for robust identification

Screen Shot 2018-04-11 at 14.39.35
Figure 1. Samples of epidermal images with low variation in images of the same species (row). From top to bottom: Ilex affinis, Myrsine guianensis, Handroanthus impetiginosus and Xylopia sericea.


Leaf epidermis images for robust identification of plants

by da Silva N. R. , daSilva Oliveira M. W., Antunes deAlmeida Filho H.  , Souza Pinheiro L. F., Rossatto D. R., Kolb R. M., Martinez Bruno O. (2015)

Núbia Rosa da Silva1,2 , Marcos William da Silva Oliveira1,2 , Humberto Antunes de Almeida Filho2 , Luiz Felipe Souza Pinheiro3, Davi Rodrigo Rossatto4, Rosana Marta Kolb3 & Odemir Martinez Bruno1,2

1 Institute of Mathematics and Computer Science, University of São Paulo, USP, Avenida Trabalhador são-carlense, 400, 13566-590 São Carlos, São Paulo, Brazil.

2 Scientific Computing Group, São Carlos Institute of Physics, University of São Paulo, PO Box 369, 13560-970, São Carlos, SP, Brazil.

3 Department of Biological Sciences, Faculty of Sciences and Languages, Univ Estadual Paulista, UNESP. Av. Dom Antônio, 2100, 19806-900, Assis, São Paulo, Brazil.

4 Department of Applied Biology, Faculty of Agriculture and Veterinary Sciences, Univ Estadual Paulista, UNESP, Via de Acesso Prof. Paulo Donatto Castellane S/N. 14884-900, Jaboticabal, São Paulo, Brazil.


in Scientific Reports  6:25994 – DOI: 10.1038/srep25994 –

Screen Shot 2018-04-11 at 14.41.36
Figure 2. Samples of epidermal images with wide variations in images of the same species (row). From top to bottom: Miconia cuspidata, Tapirira guianensis, Symplocos mosenii and Guapira noxia.

This paper proposes a methodology for plant analysis and identification based on extracting texture features from microscopic images of leaf epidermis. All the experiments were carried out using 32 plant species with 309 epidermal samples captured by an optical microscope coupled to a digital camera.

The results of the computational methods using texture features were compared to the conventional approach, where quantitative measurements of stomatal traits (density, length and width) were manually obtained. Epidermis image classification using texture has achieved a success rate of over 96%, while success rate was around 60% for quantitative measurements taken manually. Furthermore, we verified the robustness of our method accounting for natural phenotypic plasticity of stomata, analysing samples from the same species grown in different environments.

Texture methods were robust even when considering phenotypic plasticity of stomatal traits with a decrease of 20% in the success rate, as quantitative measurements proved to be fully sensitive with a decrease of 77%.

Results from the comparison between the computational approach and the conventional quantitative measurements lead us to discover how computational systems are advantageous and promising in terms of solving problems related to Botany, such as species identification.


Methods to measure stomatal and morphological features.

(a) Input image I. [6] Fig 1 (b) Result after binarization [6]


A Review: Methods of Automatic Stomata Detection and Counting Through Microscopic Images of a Leaf

by Bhaiswar N., Dixit V. V. (2016)

Nitin Bhaiswar 1 ,P.G. Student, Department of E&TC, Sinhgad College of Engineering, Vadgaon (BK), Maharashtra, India

Dr.V. V. Dixit 2 , Professor, Department of E&TC, Sinhgad College of Engineering, Vadgaon (BK), Maharashtra, India



in International Journal of Innovative Research in Science, Engineering and Technology  5(6): 10612-10617 –

Screen Shot 2018-02-07 at 21.07.50

Fig 2 (a) Response map [6] Fig 2 (b) Regions of maximum responses after Thresholding [6]


Stomata are the small pores in leaf epidermis of a plant which are important for the intake of carbondioxide and release of oxygen for the growth of plant.

Our aim is to discuss methods to design a tool which can automatically detect number of stomata present on an epidermis of a leaf and count them.

First method is by using morphological operation and another by using the template matching algorithm.

These methods also measure their stomatal and morphological features.

Screen Shot 2018-02-07 at 21.10.12

Fig.3 a) original image of species 1 [7] Fig 3b) Image after stomata segmentation of species1[7]

Measuring Stomatal Density



Measuring Stomatal Density

by Meatyard B., MacDonald M. (xxxx)

Barry Meatyard and Mary MacDonald.

in SAPS –

Science & Plants for Schools:  HYPERLINK “”

Introduction and context

Estimation of stomatal density is often done when studying photosynthesis (at GCSE and higher levels), and can offer a way of illustrating use of the graticule with post-16 students. There are a number of ways to measure stomatal density. Because of the size of stomata, you will need a reasonably good microscope for this. Your choice of magnification will depend on the leaf material that you are using, and the size of the stomata.

One popular method has been to use clear nail varnish to make an impression of the epidermis. Making the impression and viewing it under a microscope can be completed in one lesson. However, some leaves are prone to damage from the solvent in the nail varnish. The leaves absorb it, turn brown, and fail to produce any impression. Pupils lose interest and get frustrated because their leaves ‘aren’t working’. Also, for a GCSE class, several pots of nail varnish are needed so that no one is left waiting, thus adding to expense. Other methods include using Germolene New Skin and using a water-based varnish from DIY shops.


Selecting your plants

One of the best plants for doing epidermal peels is the red hot poker plant Kniphofia. Being a monocot its stomata are highly ordered in rows, but they are big and great for stomatal opening and closing using solutions of different concentrations.

Almost as good is the Elephants Ear Saxifrage Bergenia. This also peels very easily, but the stomata are smaller although clearly visible at x100 magnification. This is a dicot so the distribution is more random.

Many labs have a Pelargonium, and these can also be used for leaf peels.

Spider plants (Chlorophytum comosum variegatum) make excellent leaf peels, with particularly interesting and regular patterns of stomata along the green leaf areas only.

Stomata in Aloe epidermal peel

Photo credit :


Aloe-leaf epidermal peel – stomata

mrsonchus (2016)

– Microscopy Forum – Pictures and Videos –


I’ve been putting some freshly-cut Aloe-leaf into fixative this evening and thought I’d make a quick & dirty epidermal-peel. Stained briefly with Toluidine-blue (aq) then water-mounted with coverslip, very colourful.
Had a quick try of a cardboard ‘Matthias-arrow’ I ‘made’ when reading the great Walter Dioni’s articles when I started-out – it’s really not very good compared to the simply fantastic oblique-illumination often seen of this forum (to say the least! :oops: ) but gives a little relief at least.


Here are a few pictures, apologies for the poor quality, it was a very quick foray as I was actually fixing tissue rather than meaning to do this, but though it’d be nice to have a peek. I’ll definitely go back and do some ‘proper’ ones I think, maybe mounted in glycerin or perhaps an alcohol-based mountant, anyway here are a few pictures to peruse!


Methods to observe stomata

Screen Shot 2018-01-23 at 10.55.56


9.2 Applications and skills – 9.2.1 Counting stomata

in Philpot Education (2018)

When stomata are open, the air spaces in the spongy mesophylllayer of a leaf become continuous with the atmosphere. This means that photosynthetic gases are free to diffuse in and out of the plant. In general, carbon dioxide diffuses in through stomatawhile oxygen and water diffuse out.

Stomata are generally open during the day to allow the free exchange of photosynthetic gases, and closed at night to prevent water loss when photosynthesis is not taking place.

As a consequence, water loss is highest during the day. This is not a problem for well-watered mesophytes. However, plants that live arid conditions with saline soils – xerophytes – have special adaptations to reduce water loss by transpiration. These include:

  • a thick cuticle, giving the leaf a waxy or leathery appearance, or leaves covered in small hairs to prevent water loss through evaporation
  • stomata concentrated on lower surfaces or in deep pits protected from the wind
  • fleshy stems that store water – in the case of cacti, stems are photosynthetic and leaves are reduced to short spines
  • stomata closed during the day and open at night.

Controlling the opening and closing of stomata


Microscopy-Based Stomata Analyses

Screen Shot 2018-01-07 at 18.15.30
Fig 1. Experimental setup for stomatal aperture measurements. (a) Schematic representation of the workflow; (b) epifluorescent microscopic picture of the Arabidopsis leaf stained with rhodamine 6G; (c) the same picture as in (b) after application of the option “sharpen” in ImageJ. Bars, 50 μm.


A Rapid and Simple Method for Microscopy-Based Stomata Analyses

by Eisele J. F., Fäßler F., Bürgel P. F., Chaban C. (2016)

Department of Plant Physiology, Center for Plant Molecular Biology (ZMBP), University of Tübingen, Tübingen, Germany


in PLoS ONE 11(10): e0164576. –

Screen Shot 2018-01-07 at 18.18.42
Fig 3. Visualization of stomatal apertures in intact leaves and epidermis peels. (a,b) Epifluorescent images of intact leaves mounted in water (upper panel) and in 30% glycerol (lower panel). (a) Staining with 1 μM rhodamine 6G; (b) staining with 10 μM rhodamine 6G. (c) Photograph of leaf epidermis peels. (d) Confocal image of cells in the peeled epidermis; λexc = 488 nm, λem = 505–545 nm (upper panel); λexc = 561 nm, λem = 600–640 nm (middle panel); bright field (lower panel). Bars, 50 μm.


There are two major methodical approaches with which changes of status in stomatal pores are addressed: indirectly by measurement of leaf transpiration, and directly by measurement of stomatal apertures.

Application of the former method requires special equipment, whereas microscopic images are utilized for the direct measurements. Due to obscure visualization of cell boundaries in intact leaves, a certain degree of invasive leaf manipulation is often required.

Our aim was to develop a protocol based on the minimization of leaf manipulation and the reduction of analysis completion time, while still producing consistent results. We applied rhodamine 6G staining of Arabidopsis thaliana leaves for stomata visualization, which greatly simplifies the measurement of stomatal apertures.

By using this staining protocol, we successfully conducted analyses of stomatal responses in Arabidopsis leaves to both closure and opening stimuli. We performed long-term monitoring of living stomata and were able to document the same leaf before and after treatment.

Moreover, we developed a protocol for rapid-fixation of epidermal peels, which enables high throughput data analysis. The described method allows analysis of stomatal apertures with minimal leaf manipulation and usage of the same leaf for sequential measurements, and will facilitate the analysis of several lines in parallel.