In this work, a material recognition technology based on the backscattering field of a target with vortex beam illumination is proposed to meet the application requirements of target material recognition and classification in laser detection. Firstly, the characteristics of the backscattering light field of the target with vortex beam illumination are analyzed, and it is proved that the spatial frequency bandwidth of the specklegram increases with the increase of the topological charge of the vortex beam, so that the features of the specklegram will become more abundant. Subsequently, an experimental setup was built to record the backscattering specklegram and establish a dataset for validation. Six typical artificial neural networks (ANNs) were used to achieve the task of target material recognition. With a dataset of 1 000 samples for each of three categories, the recognition accuracy can be up to 96.89%. Finally, a comprehensive evaluation model is established when we consider the factors, including recognition accuracy, model complexity, and training time, and the performances of these ANNs are compared. Among these ANNs, ResNet-18 exhibits superior overall performance. The proposed target material recognition technique paves a new way to multi-dimensional laser detection technology.
| [1] |
Zhang Q, Pandit A, Liu Z, et al.. Non-invasive estimation of the powder size distribution from a single speckle image. Light science & application, 2024, 13: 200 J]
|
| [2] |
Zhang Q, Gamekkanda J C, Pandit A, et al.. Extracting particle size distribution from laser speckle with a physics-enhanced autocorrelation-based estimator (PEACE). Nature communication, 2023, 14: 1159 J]
|
| [3] |
Li S, Peng G, Xu D, et al.. A multi feature fusion model for surface roughness measurement of cold-rolled strip steel based on laser speckle. Measurement, 2024, 227(15): 114319 J]
|
| [4] |
Shao M, Xu D, Li S, et al.. A review of surface roughness measurements based on laser speckle method. Journal of iron and steel research, international, 2023, 30(10): 19 J]
|
| [5] |
Gao W, Du X, Wang Y, et al.. Review of laser speckle target detection technology. Chinese optics, 2020, 13(6): 1182-1193 J]
|
| [6] |
Valent E, Silberberg Y. Scatterer recognition via analysis of speckle patterns. Optica, 2018, 5(2): 204-207 J]
|
| [7] |
Deng S, Liu C, Tan Y, et al.. A combination of multiple deep learning methods applied to small-sample space objects classification. Spectroscopy and spectral analysis, 2022, 42(2): 7[J]
|
| [8] |
Li Z, Deng Z, Wu P, et al.. Surface roughness prediction based on laser speckle images and convolutional neural network-support vector regression. Laser & optoelectronics progress, 2024, 61(14): 1412006[J]
|
| [9] |
He F, Wu Q, Yang Y, et al.. Research on laser speckle image recognition technology based on transfer learning. Chinese journal of liquid crystals and displays, 2024, 48(3): 443-448[J]
|
| [10] |
Zhang T, Guo X, Fan S, et al.. AMS-Net: attention mechanism based multi-size dual light source network for surface roughness prediction. Journal of manufacturing processes, 2022, 81: 371-385 J]
|
| [11] |
Guo X, Guo X, Zou Q, et al.. FE-trans-net: feature enhancement based single branch deep learning model for surface roughness detection. Journal of manufacturing processes, 2023, 105: 324-337 J]
|
| [12] |
Ji ZSpeckle interference surface roughness measurement system based on machine learning, 2021WuhanHuazhong University of Science & Technology[D]
|
| [13] |
Su JResearch on roughness measurement of milled work pieces based on deep transfer learning and object detection, 2023GuilinGuilin University of Technology[D]
|
| [14] |
Fu Y, Zhang H, Hou J, et al.. Deep learning-based particle shape classification using low-bit-depth speckle patterns in interferometric particle imaging. Acta optica sinica, 2023, 43(22): 310-319[J]
|
| [15] |
Liu Y, Yang X, Wang J, et al.. Orthogonality of non-coaxial Laguerre-Gaussian beams. Optics express, 2024, 32(4): 4876-4886 J]
|
| [16] |
Liu WResearch on characterization of target surface roughness based on laser speck, 2024Xi’anXi’an Technological University[D]
|
| [17] |
Lu HSurface topography modeling and optical performance analysis of microstructures, 2021XiamenJimei University[D]
|
RIGHTS & PERMISSIONS
Tianjin University of Technology
PDF
