基于自动加权低秩多视角谱聚类的含噪激光波长分类

doi:10.12052/gdutxb.240058

摘要/Abstract

摘要： 激光广泛应用于加工和测量等领域，如何在有噪光源干扰下检测激光的波长变化对激光的应用具有重要意义。针对激光波长变化测量的问题，本文提出了一种用于近场光栅衍射成像的多视角谱聚类方法。首先分析对静态近场光栅衍射成像图像进行激光波长变化检测的理论可行性，然后提取衍射图像的多视角特征，最后提出自动调整视图权重的多视角低秩谱聚类方法(Self-weighting Low-rank Multi-view Spectral Clustering, SL-MVSC) 对得到的多视角光栅衍射图像数据进行分类，以实现对激光波长变化的检测。在优化过程中涉及2个自变量，其中一个变量能得到闭式解，另外一个变量的优化能转化为二次规划求解问题。本文在多种噪声干扰环境下进行了实验，实验结果表明，与现有其他方法相比，本文方法在多个聚类指标上都有更好的表现；同时，t-SNE结果表明，本文方法可以将不同簇的样本区分开来，从而证明了在静态近场光栅衍射图像中使用多视角方法对激光波长变化检测的可行性与创新性。

关键词: 激光波长分类, 谱聚类, 多视角

Abstract: Laser is widely used in machining and measurement fields. Detecting the wavelength variation of laser under the interference of noisy light sources is of great significance for its application. In this research, a multi view spectral clustering method used on Fresnel grating diffraction image is proposed to address the issue of laser wavelength variation measurement. Firstly, the theoretical practicability of using static Fresnel grating diffraction image for laser wavelength stability detection is analyzed. Then, diffraction image features from multiple views are extracted. Finally, a self-weighting low-rank multi-view spectral clustering (SL-MVSC) method is proposed to classify the obtained multi-view grating diffraction image data matrix to achieve detection of laser wavelength variation. In the optimization process, there are two variables involved, one of which can obtain a closed form solution, and the optimization of the other variable is transformed into solving a quadratic programming problem. The clustering performance of this method is tested in various noise interference environments. The experiment results show that this method performs better on several clustering performance metrices compared with other four methods. Meanwhile, the t-SNE results indicate that this method can distinguish samples from different clusters. The study proves the practicability and innovation of proposed multi-view method for detecting laser wavelength variation in static Fresnel grating diffraction image.

Key words: laser wavelength classification, spectral clustering, multi-view

中图分类号:

TP751

李陵江, 陈曙, 杨祖元. 基于自动加权低秩多视角谱聚类的含噪激光波长分类[J]. 广东工业大学学报,doi: 10.12052/gdutxb.240058

Li Ling-jiang, Chen Shu, Yang Zu-yuan. Noisy Laser Wavelength Classification Based on Self-weighting Low-rank Multi-view Spectral Clustering[J]. Journal of Guangdong University of Technology, 2024, 0(0): 1-10.doi: 10.12052/gdutxb.240058

参考文献

[1] DUTTA MAJUMDAR J, MANNA I. Laser processing of materials[J]. Sadhana, 2003, 28: 495-562.
[2] AZADGOLI B, BAKER R Y. Laser applications in surgery[J]. Annals of Translational Medicine, 2016, 4(23): 452.
[3] POEHLMANN W, VAN VEEN D, FARAH R, et al. Wavelength drift of burst-mode DML for TWDM-PON[J]. Journal of Optical Communications and Networking, 2015, 7(1): A44-A51.
[4] VLADIMIROV Y A, OSIPOV A N, KLEBANOV G I. Photobiological principles of therapeutic applications of laser radiation[J]. Biochemistry (Moscow) , 2004, 69: 81-90.
[5] FUJITA M, OHKAWA H, SOMEKAWA T, et al. Wavelength and pulsewidth dependences of laser processing of CFRP[J]. Physics Procedia, 2016, 83: 1031-1036.
[6] SANTOSA I E. A double beam Fabry-perot interferometer for measuring laser wavelength[J]. European Journal of Physics, 2021, 42(3): 035301.
[7] YAN L, CHEN B, ZHANG S, et al. Note: laser wavelength precision measurement based on a laser synthetic wavelength interferometer[J]. Review of Scientific Instruments, 2016, 87(8): 086101.
[8] CHEN X, ZHOU C, FAN D, et al. Modified frequency-shifted interferometer: encoding wavelength into phase[J]. Chinese Optics Letters, 2020, 18(10): 101203.
[9] 杨仕广, 吴海波, 焦洋. 基于光学劈尖干涉的激光波长测量系统研究[J]. 电子测量与仪器学报, 2009, 23(8): 56-60.
YANG S G, WU H B, JIAO Y. Laser wavelength measurement system based on optical wedge interference[J]. Journal of Electronic Measurement and Instrumentation, 2009, 23(8): 56-60.
[10] 张昕, 李鹏伟, 岳耀笠, 等. 一种基于3×3光纤耦合器的激光波长测量方法[J]. 光通信技术, 2023, 47(5): 84-87.
ZHANG X, LI P W, YUE Y L, et al. Laser wavelength measurement method based on 3×3 fiber coupler[J]. Optical Communication Technology, 2023, 47(5): 84-87.
[11] 王仁洲, 杨涛. 一种用激光干涉测量光波波长的新方法[J]. 大学物理实验, 2014, 27(6): 41-43.
WANG R Z, YANG T. A new method to measure wavelength of light by laser interferometer[J]. Physical Experiment of College, 2014, 27(6): 41-43.
[12] 付林, 张记龙, 王志斌. 光栅衍射法实时测量脉冲激光波长和方向[J]. 光电工程, 2005(7): 30-32.
FU L, ZHANG J L, WANG Z B. Measurement of pulsed-laser wavelength and direction in real time by grating diffraction method[J]. Opto-Electronic Engineering, 2005(7): 30-32.
[13] MOHAGHEGHIAN M, SABOURI S G. Laser wavelength measurement based on a digital micromirror device[J]. IEEE Potonics Technology Letters, 2018, 30(13): 1186-1189.
[14] O’DONNELL L, DHOLAKIA K, BRUCE G D. High speed determination of laser wavelength using Poincaré descriptors of speckle[J]. Optics Communications, 2020, 459: 124906.
[15] BRUCE G D, O’DONNELL L, CHEN M, et al. Femtometer-resolved simultaneous measurement of multiple laser wavelengths in a speckle wavemeter[J]. Optics Letters, 2020, 45(7): 1926-1929.
[16] HAPPACH M, DE FELIPE D, FRIEDHOFF V N, et al. Wavelength locking and determination in tunable lasers by gain Voltage measurement[J]. Journal of Lightwave Technology, 2021, 40(7): 2045-2051.
[17] TAO B, LEI Q, YE J, et al. Measurements and analysis of diode laser modulation wavelength at high accuracy and response rate[J]. Applied Physics B, 2020, 126: 1-7.
[18] QUAN W, LI X, LIU J, et al. Genetic algorithm for accurate modeling of distributed bragg reflector laser power and wavelength[J]. Optical Engineering, 2019, 58(2): 026108-026108.
[19] ÁLVAREZ-TAMAYO R I, PRIETO-CORTÉS P, DURÁN-SÁNCHEZ M, et al. Laser wavelength estimation method based on a high-birefringence fiber loop mirror[J]. Photonic Sensors, 2019, 9: 89-96.
[20] CHRISTENSEN M, HANSEN A K, NOORDEGRAAF D, et al. Second-harmonic-generation-based technique for examining laser diode wavelength dynamics in the μs to ms range[J]. Applied Optics, 2018, 57(6): 1432-1436.
[21] 朱咸昌, 伍凡, 曹学东, 等. 光栅衍射法测量微透镜列阵焦距时产生的光斑干扰分析[J]. 光学学报, 2011, 31(11): 178-184.
ZHU X C, WU F, CAO X D, et al. Analysis of focus dislocation induced by the microlens array measuring based on grating diffraction[J]. Acta Optica Sinica, 2011, 31(11): 178-184.
[22] KOTOV M M , DANKO V P , GOLOBORODKO A A. Simulation of Talbot effect from a binary phase grating using Fresnel integral approach[J]. Optics and Lasers in Engineering, 2021, 137: 106400.
[23] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). San Piego IEEE, 2005, 1: 886-893.
[24] OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on pattern analysis and machine intelligence, 2002, 24(7): 971-987.
[25] HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973(6): 610-621.
[26] HU Z, NIE F, CHANG W, et al. Multi-view spectral clustering via sparse graph learning[J]. Neurocomputing, 2020, 384: 1-10.
[27] NIE F, HUANG H, DING C. Low-rank matrix recovery via efficient schatten p-norm minimization[C]//Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence. Ontario: AAAI, 2012, 26(1): 655-661.
[28] ARTHUR D, VASSILVITSKII S. k-means++: the advantages of careful seeding[R]. Stanford, 2006.
[29] YOU X, LI H, YOU J, et al. Consider high-order consistency for multi-view clustering[J]. Neural Computing and Applications, 2024, 36(2): 717-729.
[30] HE Z, WAN S, ZAPPATORE M, et al. A similarity matrix low-rank approximation and inconsistency separation fusion approach for multiview clustering[J]. IEEE Transactions on Artificial Intelligence, 2023, 5(2): 868-881.
[31] ZHOU P, DU L. Learnable graph filter for multi-view clustering[C]//Proceedings of the 31st ACM International Conference on Multimedia. Ottawa: Association for Computing Machinery, 2023: 3089-3098.
[32] YANG B, ZHANG X, NIE F, et al. ECCA: Efficient correntropy-based clustering algorithm with orthogonal concept factorization[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 34(10): 7377-7390.
[33] STEINLEY D. Properties of the hubert-arable adjusted rand index[J]. Psychological Methods, 2004, 9(3): 386.
[34] WU M, SCHÖLKOPF B. A local learning approach for clustering [C]//Proceedings of the 19th International Conference on Neural Information Processing Systems. Canada: MIT Press, 2006: 1529-1536.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed