Research on Prediction of Pigment Concentration in Color Painting Based on BOA-FRNN Spectral Model
LIU Zhen1, FAN Shuo2*, LIU Si-lu2, ZHAO An-ran2, LIU Li3
1. School of Communication, Qufu Normal University, Rizhao 276826, China
2. College of Engineering, Qufu Normal University, Rizhao 276826, China
3. School of Physics and Electronic Information, Yunnan Normal University, Kunming 650500, China
Abstract：In recent years, efforts to protect cultural relics and heritage have been intensified, and the strengthening of the preservation and inheritance of historical culture has risen to the level of a national strategy. Painted cultural relics under anthropogenic, sand erosion, and photodamage, the color of cultural relics generally appeared to varying degrees of fading, discoloration, aging, shedding, and loss of disease, so that it is now difficult to see the original face of the mural painting,digital protection and restoration has become an important means of protection and inheritance of painted cultural relics. Based on the spectral reflectance of color fingerprints, this study has taken the spectral reflectance of the external manifestation of pigment composition change as the entry point andused digital methods to map the concentration of painted pigments. To quickly and accurately identify mineral pigment concentration in color painting, the Bayesian Optimization Algorithm (BOA) was used to find the optimal hyperparameters of the Feed-forward Regression Neural Network (FRNN), and a BOA-FRNN spectral model was constructed topredict pigment composition and concentration distribution mapping. Firstly, the color chart of Dunhuang mineral pigments with different concentration gradients was drawn by traditional Chinese painting techniques, and the visible spectral reflectance and chromaticity information of the color chartwas obtained by Ci64UV integrating sphere spectrophotometer.Secondly, the correlation database of pigments' spectral reflectance, chromaticity values, concentration, pigment particle size, and ingredients was constructed based on the measured data. Finally, the pigment concentration was predicted. The results were compared using the two-constant Kubelka-Munk model, BP network model, support vector machine (SVM) regression algorithm, FRNN network model, and BOA-optimized SVM. To improve the accuracy of concentration prediction and model stability, BOA was proposed to optimize the network structure, activation function, and regularization strength of FRNN. Root Mean Squared Error (RMSE) was used as the fitness function, and the optimal regression parameters were selected through iteration to train the model.The results of pigment data prediction showed that the optimal combination model was BOA-FRNN. Experimental data show that the BOA-FRNN proposed in this paper has higher accuracy. The determination coefficient R2 of the model test set was 99.55%, theroot mean square error RMSE was 1.805%. The results show that the Dunhuang pigment color database can select the required spectral reflectance more accurately and quickly, thus improving the model's efficiency and simplifying the algorithm's complexity. BOA searches for the optimal hyperparameters of FRNN and can quickly obtain the global optimal solution by iteratively updating the optimal position of hyperparameters. Compared with K-M, BP, SVM, FRNN, and BOA-SVM, the prediction accuracy and model stability are significantly improved, which meets the accuracy requirements of pigment concentration detection and is a feasible new method for fast pigment mapping.
刘 振，樊 硕，刘思鲁，赵安然，刘 莉. 基于BOA-FRNN光谱模型的彩绘颜料浓度预测研究[J]. 光谱学与光谱分析, 2025, 45(02): 322-331.
LIU Zhen, FAN Shuo, LIU Si-lu, ZHAO An-ran, LIU Li. Research on Prediction of Pigment Concentration in Color Painting Based on BOA-FRNN Spectral Model. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(02): 322-331.
[1] Ren H, Sun K, Zhao F, et al. Heritage Science, 2024, 12(1): 39.
[2] Yu T, Lin C, Zhang S, et al. International Journal of Computer Vision, 2022, 130(11): 2646.
[3] Chai B, Yu Z, Sun M, et al. Heritage Science, 2022, 10(1): 164.
[4] Moretti P, Zumbühl S, Scherrer N, et al. Color Research & Application, 2024, 49(1): 124.
[5] Shitomi R, Tsuji M, Fujimura Y, et al. Journal of the Optical Society of America A-Optics Image Science and Vision, 2023, 40(1): 116.
[6] Berns R S. Color Research & Application, 2019, 44(4): 531.
[7] Wei C A, Xie D, Wan X, et al. Fibers and Polymers, 2024, 25(6): 2139.
[8] LIU Mei-chen, XUE He-ru, LIU Jiang-ping, et al（刘美辰, 薛河儒, 刘江平, 等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2022, 42(5): 1601.
[9] Zhao Z, Wang Z, Yuan J, et al. Engineering, 2021, 7(2): 195.
[10] Sun C, Guo N, Ye L, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023, 296: 122663.
[11] Schirmacher W, Ruocco G. Condensed Matter Physics, 2023, 26: 33604.
[12] Yin J, Li N. Ore Geology Reviews, 2022, 145: 104916.
[13] Zhang P, Wang L, Fei Z, et al. Knowledge-Based Systems, 2023, 271: 110564.
[14] Li D, Liu Z, Xiao P, et al. Underground Space, 2022, 7(5): 833.
[15] Chen R, Song J, Xu M, et al. Construction and Building Materials, 2023, 394: 132127.
[16] Fan C, Lai X, Wen H, et al. Geohazard Mechanics, 2023, 1(4): 319.
[17] Mohammadi P, Kokabi A, Shahdoosti H R, et al. Materials Today Communications, 2024, 39: 109073.
[18] Anh D T, Pandey M, Mishra V N, et al. Applied Soft Computing, 2023, 132: 109848.
