READ ME File For 'Dataset for Generating images of hydrated pollen grains using deep learning'

Dataset DOI: https://doi.org/10.5258/SOTON/D2097

ReadMe Author: James A Grant-Jacob  University of Southampton https://orcid.org/0000-0002-4270-4247

This dataset supports the publication:
AUTHORS:James A. Grant-Jacob, Matthew Praeger, Robert W. Eason and Ben Mills
TITLE:Generating images of hydrated pollen grains using deep learning

JOURNAL: IOP SciNotes
PAPER DOI IF KNOWN: 


This dataset contains:

Figure_1.png
Figure_2.jpg
Figure_3.jpg
Figure_4.jpg
Figure_5.png
Table_1.txt

Figure 1. Concept: The neural network takes an image of a pollen grain’s dehydrated state and uses this to generate an image that simulates its hydrated state.  

Figure 2. Examples of experimentally obtained micrographs of (a) hydrated Ranunculus pollen grains and (b) their corresponding dehydrated state. The scale bar is the same size in all images and represents a length of 15 µm.

Figure 3. Experimentally obtained micrographs of 10 different pollen grain genera, which includes hydrated Ranunculus. The scale bar is the same size in all images and represents a length of 15 µm.

Figure 4. The first column (input) shows experimental microscope observations of the dehydrated state. The second column (actual image) shows experimental microscope observations of the hydrated state. The third column (generated image) shows an image of the simulated hydrated state (as generated by the neural network, from the image shown in the input column). The fourth column (error) shows the difference between the experimental image of the hydrated state (actual image) and the NN generated image (generated image). For the images in the fourth column, the darker the pixels, the more accurate the generation. Inset purple text in the images is the area of each pollen grain.

Figure 5. (a) Confusion matrix of predicted genus and actual genus for the identification neural network of experimental images of pollen grains and generated images of hydrated Ranunculus pollen grains. (b) Mean probability of predictions (maximum possible value of 1) of the 5 generated images of hydrated Ranunculus pollen grains shown in figure 4.

Table 1. The Structural Similarity Index Measurement (SSIM) between the generated images and actual images in figure 4, and the percentage pollen grain size increase from their initial size in the dehydrated state.

Date of data collection: 10/2020

Information about geographic location of data collection: Building 46, University of Southampton, Southampton, SO17 1BJ
 
Licence: CC-BY

Related projects:
EPSRC grant EP/N03368X/1
EPSRC grant EP/T026197/1


Date that the file was created: 04, 2022