|
|
|
|
|
|
| Training Sample Selection for Spectral Reconstruction Based on Improved K-Means Clustering |
| LIU Zhen1*, LIU Li2*, FAN Shuo2, ZHAO An-ran2, LIU Si-lu2 |
1. School of Communication, Qufu Normal University, Rizhao 276800, China
2. School of Engineering, Qufu Normal University, Rizhao 276800, China
|
|
|
|
|
Abstract Developing an efficient training sample selection method is one of the goals of spectral reflectance reconstruction. In spectral reflectance reconstruction, the training set selection method and sample capacity are strongly related to the reconstruction accuracy. The accuracy of the spectral reconstruction is affected by the unstable clustering results due to the randomness of the starting value selection and the outliers. K-means clustering has low computing complexity and great computational efficiency. Based on this, this paper proposes an improved K-means clustering training sample selection method. Firstly, the geometric center of the training sample set is used as the initial value of the clustering center; secondly, the probability density function of the spatial distribution of the samples is constructed based on the Gaussian function, and the Euclidean (Euclidean) distance is used as the measure of other clustering centers; finally, the similarity between the spectral reflectance samples in the training sample set is measured based on the intra-cluster squared difference, and the sample with the closest distance to the center in each clustering subset is used as the training samples are used to verify the effectiveness of the method. The spectral reconstruction was performed by principal component analysis. The experimental results show that the proposed method has been improved significantly compared with the traditional method, the average root-mean-square error of the reconstructed spectra is less than 4%, and the CIEDE2000 color difference is less than 3.756 7. The improved training sample selection method of K-mean clustering proposed in this paper can improve the spectral reconstruction accuracy to some extent and meet the requirements of reproducing the reproduced images.
|
|
Received: 2022-06-26
Accepted: 2022-11-29
|
|
|
|
Corresponding Authors:
LIU Zhen, LIU Li
|
|
[1] Day E A, Berns R S, Taplin L A, et al. Journal of Imaging Science and Technology, 2004, 48(2): 93.
[2] Baribeau R. 1st Int Symposium on 3D Data Processing Vision, Graphics and Image Processing, 2003: 115.
[3] Herzog P G, Knipp D, Stiebig H, et al. Journal of Electronic Imaging, 1999, 8(4): 342.
[4] Dicarlo J M, Wandell B A. J. Opt. Soc. Am. A, 2003, 20(7): 1261.
[5] WANG Ge, LI Chang-jun, ZHU Yun-long, et al（王 葛, 李长军, 朱云龙, 等）. Photographic Science and Photochemistry（感光科学与光化学）, 2005，(5): 340.
[6] Hardeberg J Y. Journal of Imaging Science and Technology, 2004, 48(2): 105.
[7] Cheung V, Westland S. Journal of Imaging Science and Technology, 2006, 50(5): 481.
[8] Mohammadi M，Nezamabadi M，Berns R S，et al. 12th Color Imaging Conference，2004: 59.
[9] Shen Huiliang, Han Tianqi, Li Chunguang. IEEE Transactions on Image Processing, 2017, 26(1): 439.
[10] Liu Zhen, Liu Qiang, Gao Guiai, et al. Optics Express, 2017, 25(11): 12435.
[11] Liu Zhen, Xiao Kaida, Pointer Michael R, et al. Sensors, 2021, 21(23): 7911.
[12] Liang Jinxing, Xiao Kaida, Hu Xinrong. Optics Express, 2021, 29(26): 43899.
[13] LIANG Jin-xing, WAN Xiao-xia（梁金星，万晓霞）. Acta Optica Sinica（光学学报）, 2017, 37(9): 0933001.
[14] LI Chan, WAN Xiao-xia, LIU Qiang，et al（李 婵, 万晓霞, 刘 强, 等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2016, 36(5): 1400. |
| [1] |
LIANG Jin-xing1, 2, 3, XIN Lei1, CHENG Jing-yao1, ZHOU Jing1, LUO Hang1, 3*. Adaptive Weighted Spectral Reconstruction Method Against
Exposure Variation[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3330-3338. |
| [2] |
WANG Yu-chen1, 2, KONG Ling-qin1, 2, 3*, ZHAO Yue-jin1, 2, 3, DONG Li-quan1, 2, 3*, LIU Ming1, 2, 3, HUI Mei1, 2. Hyperspectral Reconstruction From RGB Images for Tissue Oxygen
Saturation Assessment[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3193-3201. |
| [3] |
SUN Bang-yong1, YU Meng-ying1, YAO Qi2*. Research on Spectral Reconstruction Method From RGB Imaging Based on Dual Attention Mechanism[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2687-2693. |
| [4] |
ZUO Chu1, XIE De-hong2*, WAN Xiao-xia3. Research on Spectral Image Reconstruction Based on Nonlinear Spectral Dictionary Learning From Single RGB Image[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(07): 2092-2100. |
| [5] |
ZHAO Xiao-kang, ZHAO Xin, ZHU Qi-bing*, HUANG Min. A Model Construction Method of Spectral Nondestructive Detection for Apple Quality Based on Unsupervised Active Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(01): 282-291. |
| [6] |
MENG Fan, LIU Yang*, WANG Huan, YAN Qi-cai. Research and Implementation of High-Performance Wavemeter Based on Principle Component Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3625-3631. |
| [7] |
LIU Yu1, LI Zeng-wei2, DENG Zhi-peng1, ZHANG Qing-xian1*, ZOU Li-kou2*. Fast Detection of Foodborne Pathogenic Bacteria by Laser-Induced Fluorescence Spectrometry[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(09): 2817-2822. |
| [8] |
KANG Xiao-yan1,2, ZHANG Ai-wu1,2*, PANG Hai-yang1,2. Estimation of Grassland Aboveground Biomass From UAV-Mounted Hyperspectral Image by Optimized Spectral Reconstruction[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(01): 250-256. |
| [9] |
WANG Shu-tao, WANG Gui-chuan*, FAN Kun-kun, WU Xing, WANG Yu-tian. Inversion of Aerosol Optical Depth in the Beijing-Tianjin-Hebei Region Based on PSO Clustering Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(11): 3321-3327. |
| [10] |
FAN Xian-guang1, 2, LIU Long1, ZHI Yu-liang1, KANG Zhe-ming1, XIA Hong1, ZHANG Jia-jie1, WANG Xin1, 2*. Fast Reconstruction for Multi-Channel Raman Imaging Based on and Sample Optimization and PCA[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(08): 2495-2499. |
| [11] |
WANG Ying-jun1, 2，ZHOU Jin-song1, 2, WEI Li-dong1*, ZHANG Gui-feng1, ZHU Dong-liang3, GUO San-wei3, TANG Hong-wu3, PANG Dai-wen3. Reconstruction Simulation with Quantum Dots Spectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 869-876. |
| [12] |
CHEN Si-ming1, 3, 4, ZOU Shuang-quan1, 4*, MAO Yan-ling2, 4, LIANG Wen-xian1, 4, DING Hui1, 4. Inversion of Soil Organic Matter Content in Wetland Using Multispectral Data Based on Soil Spectral Reconstruction[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 912-917. |
| [13] |
FU Cai-li1, LI Ying1, CHEN Li-fan1, WANG Shao-yun1, WANG Wu2*. Rapid Detection of Lotus Seed Powder Based on Near Infrared Spectrum Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(02): 424-429. |
| [14] |
WANG Wu1, 2, WANG Jian-ming1, 2, LI Ying3, LI Xiang-hui4, LI Yu-rong1, 2. Study on Diversified Adulteration of Ganoderma Lucidum Spore Oil by RVM and New Clustering Algorithms[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(04): 1064-1068. |
| [15] |
WANG Jia-jia1, LIAO Ning-fang1*, WU Wen-min1, CAO Bin1, LI Ya-sheng1, CHENG Hao-bo2 . Spectral Reflectance Reconstruction with Nonlinear Composite Model of the Metameric Black [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(03): 704-709. |
|
|
|
|
