READ ME File For 'Dataset for Accurate Inverse Design of Fabry–Pérot-Cavity-Based Color Filters far beyond sRGB via a Bidirectional Artificial Neural Network'

Dataset DOI: 10.5258/SOTON/D1686

ReadMe Author: Peng Dai, University of Southampton [0000-0002-5973-9155]

This dataset supports the publication: Accurate inverse design of Fabry–Perot-cavity-based color filters far beyond sRGB via a bidirectional artificial neural network
AUTHORS: Peng Dai, Yasi Wang, Yueqiang Hu, C. H. de Groot, Otto Muskens, Huigao Duan, and Ruomeng Huang
TITLE: Accurate inverse design of Fabry–Perot-cavity-based color filters far beyond sRGB via a bidirectional artificial neural network
JOURNAL: PHOTONICS Research
PAPER DOI IF KNOWN: 10.1364/PRJ.415141


This dataset contains:
The raw data of figure 3, 4, and 6.
The dataset training neural network.
The original image of 'Haystacks end of Summer'
The reproduction of 'Haystacks end of Summer'

The figures are as follows:

Fig. 3  Forward neural network training for predicting F-P cavity structural colors. The histogram of the probability and average values of Δ𝐸2000 of the FNNs with different (a) hidden layer number, (b) neuron number per layer, and (c) the FNN with seven hidden layers and 250 neurons in each hidden layer for different dataset size. (d) The training loss curves for defining the loss function in CIE 1931-XYZ and CIE 1976-Lab color spaces. (e) The probability histogram and average values of Δ𝐸2000 comparisons while the loss function is defined in CIE 1931-XYZ color space and CIE 1976-Lab color space. (f) The selected colors in the CIE 1931-xy chromaticity diagram with the boundary of each ellipse representing the colors that have a Δ𝐸1976 of 6 to the selected color.
Fig. 4  Inverse neural network for predicting F-P cavity structural colors. (a) The bidirectional architecture with input layer of Lab values and output layer of geometric parameter D and connected to the pretrained forward neural network. (b) The schematic of different weights’ initialization positions. (c) The loss surface schematics of nonuniqueness (left) and uniqueness (right) problems, respectively. The MSEs after 200 epochs as a function of random seed, the training loss curves, the histogram of the distribution, and average values of Δ𝐸2000 of the INNs with (d)–(f) different numbers of hidden layers and (g)–(i) different numbers of neurons per layer.
Fig. 6  Transmissive spectra and corresponding CIE 1931-RGB tristimulus values for the designed colors. The transmissive spectra (black line) and the contribution from the three stimuli (shades underneath the line) for the (i, ii, iii) blue, (iv, v, vi) green, and (vii, viii, ix) red color designed by the INN in this work. Within each figure, the middle row figure presents the original design, while the top and bottom figures represent the spectra from a 10 nm thinner layer and a 10 nm thicker dielectric layer. (b) The CIE 1931-RGB tristimulus values as a function of dielectric layer thickness for the blue, green, and red colors, respectively. The CIE 1931-RGB tristimulus values of the targeted colors are also included (dotted lines) for comparison.


Date of data collection: December 2019 to September 2020

Information about geographic location of data collection: United Kingdom, China

Licence: No

Related projects: International Exchange Scheme (IEC\NSFC\170193) between Royal Society (UK) and the National Natural Science Foundation of China (China)


Date that the file was created: June, 2021