Colorimetric characterization of the wide-color-gamut camera using the multilayer artificial neural network

Abstract

In order to realize colorimetric characterization for the wide-color-gamut camera, we propose using the multilayer artificial neural network (ML-ANN) with the error-backpropagation algorithm, to model the color conversion from the RGB space of camera to the XYZ space of the CIEXYZ standard. In this paper, the architecture model, forward-calculation model, error-backpropagation model, and the training policy of the ML-ANN were introduced. Based on the spectral reflectance curves of the ColorChecker-SG blocks and the spectral sensitivity functions of the RGB channels of typical color cameras, the method of producing the wide-color-gamut samples for the training and testing of the ML-ANN was proposed. Meanwhile, the comparative experiment employing different polynomial transforms with the least-square method was conducted. The experimental results have shown that, with the increase of the hidden layers and the neurons in each hidden layer, the training and testing errors can be decreased obviously. The mean training errors and mean testing errors of the ML-ANN with optimal hidden layers have been decreased to 0.69 and 0.84 (color difference of CIELAB), respectively, which is much better than all the polynomial transforms, including quartic polynomial transform.

Color Conversion of Wide-Color-Gamut Cameras Using Optimal Training Groups

“…The multi-layer BP artificial neural network (ML-BP-ANN) can also be used to perform the conversion from the [R, G, B] space to the [X, Y, Z] space in the case of wide color gamut [17]. The architecture of an ML-BP-ANN is shown in Figure 2, where W (0) , W (1) , and W (q) denote the link weights, and θ denotes the threshold of the neurons, and a i , b j , d p denote the output values of the neurons in each layer, respectively.…”

“…In order to obtain samples with wide color gamut, the spectral reflectance curves of ColorChecker-SG F3 and F4, as shown in Figure 4a, were used, respectively, to generate samples distributed on the whole CIE1931XYZ space. The method for the generation of wide-color-gamut samples can be found in the reference [17]. Figure 5a,d…”

“…In order to obtain samples with wide color gamut, the spectral reflectance curves of ColorChecker-SG F3 and F4, as shown in Figure 4a, were used, respectively, to generate samples distributed on the whole CIE1931XYZ space. The method for the generation of wide-color-gamut samples can be found in the reference [17]. Figure 5a,d It should be noted that, in the experiment, the CIE illuminant D65 was used as the light source S(λ i ) in Formulas ( 1) and ( 2), respectively, and the R, G and B values were normalized to 255 according to the white point.…”

“…Until now, different kinds of colorimetric characterization methods have been developed, including polynomial transforms [ 10 , 11 , 12 , 13 , 14 , 15 , 16 ], artificial neural networks (ANN) [ 17 , 18 , 19 , 20 , 21 , 22 , 23 ], and look-up tables [ 24 ]. In 2016, Gong et al [ 12 ] demonstrated a color calibration method between different digital cameras with ColorChecker SG cards and the polynomial transform method and achieved an average color difference of 1.12 (CIEDE2000).…”

Support vector machine-based method for colorimetric characterization of computer-controlled liquid crystal displays

“…The accuracy of colorimetric characterization can be optimized by choosing an adequate basis function. Li et al 33 propose using the multilayer ANN (ML-ANN) with the error-backpropagation algorithm, to model the color conversion from the RGB space of camera to the XYZ space of the CIEXYZ standard. In 2000, Hong et al proposed a polynomial regression method for the colorimetric characterization of an imaging system.…”