Next Article in Journal
Preliminary Evaluation of Spherical Over-Refraction Measurement Using a Smartphone
Previous Article in Journal
Impact of Corneal-Hydration-Induced Changes in Ablation Efficiency During Refractive Surgery
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Research on Enhancing Target Recognition Rate Based on Orbital Angular Momentum Spectrum with Assistance of Neural Network

School of Physics, Harbin Institute of Technology, Harbin 150001, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Photonics 2025, 12(8), 771; https://doi.org/10.3390/photonics12080771
Submission received: 4 July 2025 / Revised: 22 July 2025 / Accepted: 29 July 2025 / Published: 30 July 2025
(This article belongs to the Special Issue Advancements in Optics and Laser Measurement)

Abstract

In this paper, the single-mode vortex beam is used to illuminate targets of different shapes, and the targets are recognized using machine learning algorithms based on the orbital angular momentum (OAM) spectral information of the echo signal. We innovatively utilize three neural networks—multilayer perceptron (MLP), convolutional neural network (CNN) and residual neural network (ResNet)—to train extensive echo OAM spectrum data. The trained models can rapidly and accurately classify the OAM spectrum data of different targets’ echo signals. The results show that the residual network (ResNet) performs best under all turbulence intensities and can achieve a high recognition rate when C n 2 = 1 × 10 13   m 2 / 3 . In addition, even when the target size is η = 0.3 , the recognition rate of ResNet can reach 97%, while the robustness of MLP and CNN to the target size is lower; the recognition rates are 91.75% and 91%, respectively. However, although the recognition performance of CNN and MLP is slightly lower than that of ResNet, their training time is much lower than that of ResNet, which can achieve a good balance between recognition performance and training time cost. This research has a promising future in the fields of target recognition and intelligent navigation based on multi-dimensional information.

1. Introduction

In laser-active target recognition, the laser echo signal carries information about the target’s shape, size, material, reflectivity, and other properties. Target recognition can be achieved by processing characteristic information such as the echo signal’s amplitude, phase, frequency, and polarization. The traditional Gaussian beam has limited imaging resolution, and its propagation is greatly affected by the environment, with a limited range of action and insufficient adaptability, which limits its application in complex and long-distance target recognition. In recent years, due to their unique helical phase and polarization characteristic [1], vortex beams have been widely used in optical manipulation [2,3], quantum communication [4,5], imaging technology [6], underwater communication [7,8] and other fields. This paper improves the accuracy of target recognition by processing the orbital angular momentum (OAM) spectral information carried in the echo signals of the emitted vortex beam.
When vortex beams propagate through the atmosphere, they experience phase distortion, changes in intensity distribution, and dispersion of orbital angular momentum (OAM) modes. These effects degrade or distort the information carried by the originally pure OAM modes. To mitigate these issues, adaptive correction algorithms—such as the stochastic parallel gradient descent (SPGD) method [9] and the Shack-Hartmann method [10]—are required. Among the Gerchberg–Saxton (GS) algorithm, the GS iterative optimization phase recovery algorithm is the most widely used method, which works on the principle that generating pre-compensation phases can effectively counteract phase perturbations caused by the atmosphere. In 2017, Fu et al. [11] modified the GS algorithm tailored for OAM beam phase recovery in turbulent atmospheres, demonstrating mode purity restoration compared to traditional approaches. In 2018, Li et al. [12] systematically examine advancements in atmospheric turbulence compensation for OAM communication systems, highlighting techniques like phase retrieval algorithms, adaptive optics, and hybrid methods. Similarly, in 2022, Zhao et al. [13] proposed a modified GS algorithm-based wavefront sensorless adaptive optics system to compensate for atmospheric turbulence-induced phase distortions in OAM beams, achieving better compensation performance compared to traditional methods. In 2024, Cui et al. and Wang et al. [14] used orbital angular momentum spectra for target shape recognition and compensated for the distorted phase of different target echo light fields with the GS algorithm to restore the OAM spectrums of the echo light field and improve the target recognition rate. However, the GS algorithm has some limitations: its convergence depends on the initial guess and the choice of constraints, and it has a high computational complexity in the processing of complex wavefronts, which may result in failure to converge or require a large number of iterations, limiting its efficiency and applicability.
In recent years, the development of neural networks has offered new possibilities for the recognition of vortex light OAM [15,16,17,18,19]. First, the adaptive learning ability of neural networks enables models to be continuously optimized to handle complex problems without the need for precise physical modeling. In addition, neural networks support real-time and large-scale data analysis, which greatly improves the efficiency and accuracy of target recognition. This paper will use three different neural networks: multi-layer perceptron (MLP) [20], convolutional neural network (CNN), and residual network (ResNet) [21], trained with a large amount of OAM spectral data, which can quickly and accurately classify the OAM spectral characteristic of different target echo signals. Even when the turbulence intensity is high, the three networks can still maintain high recognition rates. This study has broad application prospects in areas such as target recognition based on multi-dimensional information and intelligent navigation.

2. Methods

2.1. Orbital Angular Momentum Spectrum Theory

The Laguerre–Gauss beam (LG) is the most typical and commonly used vortex beam. The expression for an LG propagating along the z-direction in free space in cylindrical coordinates is expressed as follows [22,23]:
E r , z = 2 p ! π p + l ! 1 ω z 2 r ω z l exp r 2 ω 2 z L p l 2 r 2 ω 2 z   × exp i 2 p + l + 1 tan 1 z / z R i k r 2 z 2 z 2 + z R 2 exp i l ϕ ,
where p is the radial exponent, l is the topological charge number of the vortex beam, is the waist radius of the beam, r is the distance from the beam to the propagation axis, L p l is the Laguerre polynomial, z R is the Rayleigh distance, k is the wave number of the light wave, is the azimuth angle, 2 p + l + 1 tan 1 z / z R is the Kuy phase shift, and z is the axial propagation distance. Since the OAM states with different topological charges are orthogonal to each other, it is possible to expand any beam with the base exp i l φ , where a l is the expansion coefficient:
E x , y , z = 1 2 π l = + a l r , z exp i l φ .
a l r , z = 1 2 π 0 2 π E x , y , z exp i l φ d φ .
Integrating the expansion coefficient over the entire region can yield the energy on this helical harmonic:
C l = 0 a l r , z 2 r d r .
This value is independent of the z-coordinate, and thus the relative energy of the harmonic can be obtained.
R l = C l q = + C q .
The formula represents the energy ratio of each OAM mode of the beam, which is the orbital angular momentum spectral data we measured.
The method for obtaining the OAM spectrum of the target signal is as shown in Figure 1. First, a laser with a wavelength of 532 nm is emitted using a laser, and a single-mode forked grating is loaded onto SLM1 through a spatial light modulator 1 (SLM1). A single-mode vortex beam is generated using the grating diffraction method [24,25,26,27,28,29]. When discussing the influence of atmospheric turbulence, the power spectrum inversion method is used to simulate the disturbance of atmospheric turbulence to the light field in this study. The superimposed phase of the turbulent screen of the Von Karman model [30,31,32] and the fork grating is loaded on SLM1, and the parameters of atmospheric turbulence are: The inner scale l0 = 0.0003 m, the outer scale L0 = 50 m and four kinds of atmospheric turbulence intensity ( C n 2 = 1 × 10 15   m 2 / 3 , C n 2 = 1 × 10 14   m 2 / 3 , C n 2 = 1 × 10 13   m 2 / 3 , C n 2 = 1 × 10 12   m 2 / 3 ) can be obtained by changing the refractive index constant of the atmosphere and taking successively.
With increasing of the refractive index constant C n 2 , the distortions caused by the turbulence become more severe, resulting in greater phase aberrations and significant changes in the OAM spectrum, as is shown in Figure A1 in Appendix A. It is worth noting that we just consider the influences of atmospheric turbulence in the distance of 100 m using a modified von Kármán spectrum, which enables us to isolate and analyze the effects of atmospheric turbulence without introducing additional variables related to different distances.
The first-order diffraction modulated signal is selected by using a 4F system with an aperture. After the beam is emitted to the target surface through a beam splitter (BS) and an echo signal is generated, a part of the scattered light is focused onto the CCD by the lens to capture the intensity distribution; the other part is demodulated through SLM2, which sequentially loads the demodulation phase from −10 to 10 orders, and the corresponding reverse-ordered beam is demodulated to the fundamental mode. For example, when there is an OAM component of l = 2 in the echo signal, loading a demodulation phase with l = −2 onto the SLM2 can demodulate the l = 2 component into a fundamental Gaussian beam with l = 2 − 2 = 0. The demodulated fundamental mode Gaussian beam is coupled into a single-mode fiber. The photon counter is used to record the number of photons received within a fixed time period. After normalization, it is used as an indicator of the intensity of each OAM component to obtain the OAM spectral information. The target shapes are equilateral triangles, squares, regular pentagons and circles. In this study, the target size η is defined as the ratio of the distance between the geometric centers and vertices of each shape to the scale of the light field screen. The definition of target size η as the ratio of the distance from the geometric center to the vertices of the shape relative to the optical field screen scale is intrinsically tied to the beam waist radius. This normalization ensures that different targets maintain consistent relative proportions with the beam waist, enabling fair comparisons across varying shapes and experimental conditions.

2.2. OAM Spectral Characteristic of the Vortex Beam After Being Reflected by Targets of Different Shapes

First, we investigated the effects of targets with different shapes (triangle, square, pentagon, circle) on the OAM spectrum of the echo light field, as shown in Figure 2. The parameters are set as follows: The beam waist radius is ω = 6 mm, the distance is z = 100 m, the target size is η = 0.2 , and the topological charge of the emitted signal is 3. Target reflection induces modal dispersion in the optical angular momentum, manifested by enhanced OAM spectral components at kn-mode separation from the incident beam—here defined as the target’s k-order modal dispersion characteristic. Here k is an integer, and n represents the number of symmetry axes of the target. For a circle, which can be regarded as having countless axes of symmetry, the degree of dispersion of its OAM spectrum is relatively low and can be omitted. For the same target size, the relative power of the characteristic order of the triangle is the largest, followed by the square, and the pentagon is the smallest. Because the target with the smaller interior angle has a larger area of unreflected light spot, which makes the target with the smaller interior angle reflect the OAM spectral dispersion characteristic more prominently.
The following formula can be used to describe the characteristic of OAM spectral dispersion for targets of different shapes:
R n l = k a k l + k n .
l represents the vortex beam with topological charge l, a k is the expansion coefficient, k is an integer, and n is the number of symmetry axes of the target.
In addition, we also considered using a superposition state of multi-mode vortex beams as the emitted beam, but it is worth noting that illuminating a target with multi-mode vortex beams may actually reduce the proportion of modes containing target feature information, as shown in Figure 3a,b. It can be seen that the ±4 superposition state diffuses its OAM component towards l = −7, −1, 1, 7 after being reflected by the triangular target. However, the relative power of the ±1-order dispersion characteristics of a single topological charge of 4 (l = 1, 7) is higher than that of the main dispersion characteristics of the ±4 superposition state (l = −7, −1, 1, 7). Moreover, if we employ a ±4 superposition state, the dispersion features of different targets are overly complex and more likely to be confused, making it more difficult for neural networks to learn and classify. For example, when we use a ±4 superposition state to illuminate a pentagon, the dispersion feature of the pentagon contains l = −4 + 5 = 1 and l = 4 − 5 = −1, which has a repetition of features with a triangle (l = −7, −1, 1, 7). Furthermore, we use 1, 3, and 5 vortex beam superposition states to illuminate a triangular target, as shown in Figure 3c; the target information contained in the echo signal is even less regular, with almost no significant target features. It is also difficult to maintain stability under atmospheric turbulence perturbations. Therefore, we mainly employ single-mode vortex beams for target recognition in this article; the recognition results of multi-mode vortex beam recognition can be used as references.

2.3. Neural Network Structure Analysis and OAM Spectrum Data Training Method

Three neural network architectures are used in this study to handle the recognition and classification tasks of angular spectral data: MLP, 1D-CNN [33], and 1D-ResNet [34]. These three networks take advantage of the strengths of fully connected layers, convolutional layers, and residual blocks, as is shown in Figure A2 of Appendix B, respectively, to identify and classify the OAM spectra of echo signals from four types of targets (triangle, square, pentagon, and circle). MLP passes through five fully connected layers (with 128, 256, 512, 256, and 128 neurons, respectively) and ultimately outputs four types of target categories, and the number of neurons and layers we employ has been carefully adjusted to achieve the highest recognition accuracy for MLP under strong turbulence conditions. MLP is simple to design and easy to implement, but it may need more datasets and the construction of more fully connected layers to achieve better recognition performance in strong turbulence. In the proposed CNN, two convolutional-pooling stages with increasing channel dimensions progressively extract spatial features, which are flattened and transformed by two fully connected layers to generate final predictions among four target classes. Owing to its parameter-sharing architecture and hierarchical feature extraction capability, the CNN demonstrates higher training efficiency compared to conventional models. Finally, we utilize a one-dimensional ResNet, which solves the vanishing gradient problem of deep networks through residual blocks, enabling ResNet18 to build deep networks and improve the accuracy and stability of the model. The simplified 1D-ResNet model is designed for 21-length input sequences, featuring an initial convolution layer followed by residual blocks with increasing channel dimensions. Despite the low dimension of the input data, we choose CNN and ResNet mainly for the following reasons. The OAM spectra of different targets have spatial characteristics. When dealing with one-dimensional sequence data with spatial characteristics, the convolution operation of 1D-CNN can utilize the local structure of the data effectively, thus having strong spatial feature extraction ability and maintaining high computational efficiency in strong turbulence. Meanwhile, ResNet, with its cross-layer characteristic fusion mechanism achieved through residual connections, can extract deep characteristics from complex data when strong turbulence interference causes degradation of OAM spectral characteristic; thus, it can show better recognition performance. We will further verify the feature extraction capability of ResNet in Section 3.
In this paper, the distance is set to 100 m. A total of 8000 sets of OAM spectral data collected from four targets exposed to four levels of atmospheric turbulence are divided into a training set and a test set in an 8:2 ratio. These datasets are then fed into the aforementioned three network models via batch processing for training. The models are trained with a batch size of 32, where the initial learning rate is set to 0.001, which has the best recognition performance after our adjustment and validation. All experiments are conducted on an NVIDIA RTX 2060 GPU,(Manufacturer: NVIDIA Corporation, Santa Clara, United States). To prevent overfitting, we implement early stopping when the loss plateaus for 10 consecutive epochs. These three models are trained using the cross-entropy loss function and the Adam optimizer. The expression of the cross-entropy loss L is
L = 1 N i = 1 N c = 1 C y i , c log ( y i , c ^ ) ,
where N is the number of samples, C is the number of categories (here C is 4), y i . c is the true label (0 or 1) that sample i belongs to category c, and y i . c ^ is the model’s predicted probability that sample i belongs to category c.
First, we use a vortex beam with a topological charge of 3 as the emitted signal when C n 2 = 1 × 10 14   m 2 / 3 . We take the beam waist radius ω = 6 mm, the distance z = 100 m, the target size η = 0.2 , and trained with the OAM spectral data of the echo signal. As can be seen from the loss curves shown in Figure 4, the training loss and test loss of both MLP and ResNet decrease rapidly at the beginning and then stabilize, showing good convergence; although CNN converges more epochs than MLP and ResNet, it also converges rapidly in the end.

3. Results and Discussion

3.1. The Impact of Atmospheric Turbulence Intensity on Recognition Rate

In this section, we will study the influence of the distortion of vortex light in atmospheric turbulence on the target recognition rate. The topological charge of the emitted light is 3, and all parameters of the emitted light, target size and distance are consistent with those in 2.3. We will also recognize 400 groups of OAM spectra of the four types of targets echo signals for each turbulence intensity using the three trained neural networks. As shown in Figure 5, the recognition rates of MLP, CNN and ResNet are all close to 100% under conditions of C n 2 = 1 × 10 15   m 2 / 3 and C n 2 = 1 × 10 14   m 2 / 3 , and decrease to 92%, 90.75% and 95.5%, respectively, with the increase in turbulence intensity to C n 2 = 1 × 10 13   m 2 / 3 . When the turbulence intensity increases further to C n 2 = 1 × 10 12   m 2 / 3 , due to the excessively high atmospheric turbulence intensity at this time, the beam’s wavefront distortion becomes severe, leading to the failure of the OAM spectrum in the echo signal. Consequently, the recognition rates of all three types of networks experienced a sharp decline, dropping below 50%. Further, we construct confusion matrices for identifying different targets under four kinds of turbulence intensity, as shown in Figure 6. It can be seen that under conditions of C n 2 = 1 × 10 15   m 2 / 3 and C n 2 = 1 × 10 14   m 2 / 3 , the three networks achieve 100% recognition rates for targets of all shapes, but when the turbulence intensity reaches C n 2 = 1 × 10 13   m 2 / 3 , recognition rates of the three networks for pentagons and circles significantly reduce. However, the recognition rate for triangles remains at a relatively high order. This is because the relative power of the dispersion characteristic of the pentagon is too low, and the target characteristic is easily lost under strong turbulence, which causes all three models to easily confuse the pentagon with the circle. The relative power of the dispersion characteristic of triangular targets is relatively high, and they can still maintain high recognition rates under strong atmospheric turbulence disturbances. At the same time, we find that compared with the other two networks, the confusion matrix of ResNet still maintains a higher diagonal value when C n 2 = 1 × 10 13   m 2 / 3 , showing stronger stability and generalization ability. When C n 2 = 1 × 10 12   m 2 / 3 , the confusion matrices of the three networks deteriorate further, it is worth noting that all the characteristics of the targets are completely destroyed, at which point the OAM spectral information is almost ineffective, and the recognitions are severely confused, and none of the three neural networks are capable of extracting features effectively from the invalid OAM spectrum in the case of all topological charges, resulting in a sharp decline in recognition accuracy. Thus, our neural networks mainly reach a high recognition rate when atmospheric turbulence is within the range of C n 2 = 1 × 10 15   m 2 / 3 to C n 2 = 1 × 10 13   m 2 / 3 .
It is worth noting that although CNN’s recognition rate is slightly lower in the case of strong atmospheric turbulence ( C n 2 = 1 × 10 13   m 2 / 3 ), the training time of CNN is much lower than that of MLP and ResNet. Meanwhile, when the MLP employs fewer fully connected layers (128-256-128), its recognition rate is 86.25%, which is much lower than that of the CNN (90.75%), as is shown in Table A1 in Appendix A. Therefore, in cases where there is a constraint on training time cost, using a simple CNN to train OAM data and recognize targets is also a very good choice, as is shown in Table A2.

3.2. Impact of Emission Beam Topological Charge on Recognition Rate

In this section, we will discuss the influence of the topological charge of the emitted light on the recognition rate. Parameters such as the beam waist radius, target size and distance are all the same as those in 3.1. In this paper, the k-order dispersion characteristic of the target is defined as OAM spectral components at kn-mode separation from the incident beam. Since the relative power of each target’s −1-order dispersion characteristic is the largest, we use them to represent the degree of dispersion of different targets’ OAM spectrum. As shown in Figure 7a, with the increase in topological charge, the spiral phase is more complex, which is more susceptible to the geometric characteristics of the target, so the dispersion degree of the OAM spectrum of each target echo signal also increases. It is worth noting that this phenomenon is inherently determined by the field properties of vortex beams with different topological charges. Taking the pentagonal as an example, as shown in Figure 7b, the −1-order dispersion characteristics of emitted vortex beams with different topological charges increase first and then decrease as the target size increases. But when comparing the relative power of −1-order dispersion characteristics across various topological charges under identical target size η , we can conclude that vortex beams with higher topological charges exhibit more pronounced −1-order dispersion characteristics.
In order to achieve better training performance and to control variables for a clearer investigation of the ability of emitted light to reflect target characteristics, datasets with different topological charges are trained separately. As shown in Figure 8, when the topological charge of the emitted beam is increased from l = 1 to l = 5 under the condition of C n 2 = 1 × 10 13   m 2 / 3 , we can observe the tendency that the recognition performance increases with the increase in topological charge. However, when l is further increased to 6 and 7, the recognition rates of the three networks at lower orders tend to decline compared to l = 5 when C n 2 = 1 × 10 13   m 2 / 3 . As shown in Figure 9, we furthermore construct matrices of the recognition rates of the three networks for the four specific patterns at l = 1, 5, 7 under different atmospheric turbulence. When l = 1, under medium and strong turbulence, the recognition rates of the three networks for each target (especially the pentagon) are significantly lower compared to when l = 3. When the topological charge of the emitted beam increases to 5, ResNet and MLP achieve 100% recognition for all targets. Further, when the topological charge of the emitted light is increased to 7 as the turbulence intensity reaches C n 2 = 1 × 10 13   m 2 / 3 , we find that due to the more complex light intensity and phase distribution of the vortex beam with l = 7, which is more susceptible to the disturbance of strong turbulence, the purity of the topological charge at the center of the beam decreases, resulting in a lower recognition rate for circular targets than other targets. From the above discussion, it can be seen that by appropriately increasing the topological charge of the emitted beam to improve the dispersion, the recognition rate of targets such as triangles, squares, and pentagons can be effectively enhanced. However, the topological charge of the emitted beam should not be increased too much either, as higher-order vortex beams are more susceptible to atmospheric turbulence. Meanwhile, when topological charge increases to 6, the impact of atmospheric turbulence disturbance on the recognition rate is greater than the effect of the increase in relative power when C n 2 = 1 × 10 13   m 2 / 3 , which ultimately leads to a decrease in recognition accuracy.
In addition, we also compared the recognition rates of the vortex beam with topological charge of 4, the ±4 vortex beam superposition state, and the 1, 3, and 5 superposition state mentioned in Section 2.2 as the emitted beam when C n 2 = 1 × 10 13   m 2 / 3 , as shown in Table 1. We can see the single-mode vortex beam has better recognition performance than the superposition states, which is consistent with the conclusion in Section 2.2. Interestingly, the phenomenon is more evident from the performance of the MLP because of its lack of spatial feature extraction ability. However, we can also change the topological charge of the emitted single-mode vortex beam and integrate the recognition results of multiple topological charges (such as the result of the emitted topological charge being l = 3, l = 5, l = 7, respectively) and make a comprehensive analysis and judgment to ultimately identify the target more accurately.
In a complex atmospheric turbulence environment, different neural networks show differences in recognition performance closely related to their structural characteristics. ResNet, with its cross-layer characteristic fusion mechanism achieved through residual connections, can extract deep characteristic from complex data when turbulence interference causes degradation of OAM spectral characteristic, thus maintaining the highest recognition rate at all turbulence intensities; CNN excels at capturing the residual local spatial patterns after nonlinear distortion through the convolution features of local receptive fields and weight sharing; MLP relies on the global mapping advantage of the fully connected layer to quickly establish end-to-end classification decision boundaries when the features are not complex, but its lack of spatial feature extraction ability leads to a sudden drop in performance when the spatial features are deep and complex. Moreover, when the turbulence intensity is extremely high ( C n 2 = 1 × 10 12   m 2 / 3 ), the echo signal wavefront distortion is severe, the OAM spectral data becomes extremely chaotic, and all three networks have difficulty extracting the chaotic and complex data characteristic, especially MLP, whose fully connected structure fails to learn the characteristic of circles, pentagons, and squares at l = 1 and l = 7, and thus recognizes all the targets as triangles.

3.3. The Impact of Target Size on Recognition Rate

This section examines the effect of target size on recognition rate, with the target size gradually increasing from 0.2 to 0.3 under the condition of C n 2 = 1 × 10 14   m 2 / 3 and l = 5. As shown in Figure 10a, we find that the CNN’s recognition rate drops sharply to 91% when η reaches 0.3; MLP’s recognition rate drops from 100% to 91.75% when η reaches 0.3; by contrast, ResNet is least affected by the target size and still maintains a recognition rate of 97% when η = 0.3 . All three networks tend to confuse circles with pentagons, which also confirms the conclusion that the OAM spectral dispersion characteristic is positively correlated with the recognition rate. As shown in Figure 10b, with the increase of η , the relative power of the −1-order dispersion characteristic of the targets decreases, especially for the pentagon. When η increases to 0.3, its OAM spectral dispersion characteristic almost disappears, which leads to a sharp decline in the recognition ability of the three networks for pentagons and circles. From the above results, it can be seen that the target size should not be too large, because at this time the relative power of the −1-order dispersion characteristic is too low to clearly reflect the characteristic of the target, resulting in a decrease in recognition rate, especially for targets with large interior angles such as pentagons.
From the recognition performance of the three networks at medium turbulence intensity, when the actual value of the OAM spectral dispersion characteristic of the target echo signal is very small (such as a pentagon), ResNet, due to its internal residual block and skip connection design, can effectively enhance the transmission efficiency of the information flow, ensuring that even tiny dispersion characteristics can be fully utilized and transmitted. This maintains the effectiveness of learning in deep network structures, and the recognition rate is less affected by the size of the target.

4. Conclusions

In this paper, single-mode vortex beams are used to illuminate targets of different shapes, and the targets are recognized by the OAM spectral information of the echo signals. MLP, CNN and ResNet are used to train a large amount of echo OAM spectral data to achieve the recognition and classification of the targets. All three networks are able to quickly, accurately and stably classify the OAM spectral data of different target echo signals under the disturbance of strong atmospheric turbulence. Among them, ResNet, with its cross-layer characteristic fusion mechanism achieved through residual connections, can extract deep characteristics from complex data when turbulence interference causes degradation of OAM spectral characteristics and still maintain high recognition rates when C n 2 = 1 × 10 13 m 2 / 3 . Secondly, since the relative power of the −1-order dispersion characteristic of the target decreases as the target size η increases; the recognition rate also decreases accordingly. ResNet enhances gradient flow and feature reuse through residual blocks and skip connections, demonstrating the strongest adaptability to the increasing of η , with a recognition rate of 97% even when η reaches 0.3. MLP and CNN are less robust to target size, with recognition rates of 91.75% and 91%, respectively. Although CNN and MLP have slightly lower recognition performance than ResNet in general, they take much less time to train than ResNet, achieving a good balance between recognition performance and training time cost. Our proposed models not only outperform traditional methods and simpler classifiers but also offer comparable or superior performance to the GS algorithm while requiring fewer computational resources, as is shown in Table A3.
This paper studies the target recognition rates of different neural networks based on the OAM spectrum of echo signals in an atmospheric turbulent environment. In this paper, we assume that the targets being detected are flat and free of undulations. However, we plan to expand our study to include the influence of surface roughness on recognition performance in future work. Furthermore, we may utilize perfect vortex beams or Bessel–Gaussian beams as the emitted beams and compare the results with those of LGs to investigate whether using perfect vortex beams as the emitted source can alleviate the disturbance caused by atmospheric turbulence and further enhance the recognition rate. Subsequently, our research can be used for the recognition and classification of asymmetric targets and has broad application prospects in areas such as multi-dimensional information-based target recognition and intelligent navigation.

Author Contributions

Conceptualization, G.C.; methodology, G.C. and H.W.; software, G.C.; validation, H.Y.; formal analysis, G.C.; investigation, X.L.; resources, C.C.; data curation, G.C.; writing—original draft preparation, Z.S. and D.W.; writing—review and editing, Z.S.; visualization, X.L.; supervision, Z.Z. and Y.Z.; project administration, Z.Z. and Y.Z.; funding acquisition, Z.Z. All authors have read and agreed to the published version of the manuscript.

Funding

This work is supported by the Heilongjiang Provincial Natural Science Foundation for Excellent Young Scholars (YQ2024F012); in part by the Fundamental Research Funds for Central Universities under Grant FRFCU5710050722, Grant FRFCU5770500522, and Grant FRFCU9803502223.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Data underlying the results presented in this paper are not publicly available at this time but may be obtained from the authors upon reasonable request.

Conflicts of Interest

The authors declare no conflicts of interest.

Appendix A

In Appendix A, we discuss the phase distortion of vortices caused by atmospheric turbulence intensity. With increasing of C n 2 , the distortions caused by the turbulence become more severe, resulting in greater phase aberrations and significant changes in the OAM spectrum. As is shown in the figure, when C n 2 = 1 × 10 15   m 2 / 3 , the phase distortion and OAM dispersion of the beam are relatively small. However, when C n 2 = 1 × 10 12   m 2 / 3 , the distortion and dispersion of the optical field are very significant, as shown in Figure A1.
Figure A1. Phase of optical field and OAM spectrum distortion (a) C n 2 = 1 × 10 15   m 2 / 3 . (b) C n 2 = 1 × 10 14   m 2 / 3 . (c) C n 2 = 1 × 10 13   m 2 / 3 . (d) C n 2 = 1 × 10 12   m 2 / 3 .
Figure A1. Phase of optical field and OAM spectrum distortion (a) C n 2 = 1 × 10 15   m 2 / 3 . (b) C n 2 = 1 × 10 14   m 2 / 3 . (c) C n 2 = 1 × 10 13   m 2 / 3 . (d) C n 2 = 1 × 10 12   m 2 / 3 .
Photonics 12 00771 g0a1

Appendix B

First, we constructed a multilayer perceptron (MLP) consisting of six linear layers: five hidden layers and one output layer. After each hidden layer, the ReLU activation function is applied to introduce nonlinearity, thereby enhancing the model’s learning capability. As shown in Figure A2a, the input layer receives 21 angular spectrum features, which pass through five hidden layers with gradually changing numbers of nodes (128, 256, 512, 256, and 128), and finally map to four output nodes corresponding to four categories of graphical classes.
Second, this paper designs a simplified convolutional neural network (CNN) that combines one-dimensional convolutional layers, max pooling layers, and fully connected layers, making it suitable for processing angular spectrum data with potential spatial structure or local correlations. Through convolution operations, the network automatically learns local features from the OAM spectral data, and the pooling layers reduce feature dimensions and enhance the model’s translation invariance. As illustrated in Figure A2b, after two rounds of convolution and pooling, the results are flattened and further processed by two fully connected layers for feature integration, ultimately mapping to the four target categories.
Finally, this paper implements a residual network (ResNet) based on the ResNet18 architecture, a deep network framework that addresses the problem of gradient vanishing in deep networks through residual blocks and facilitates efficient information transfer. The core of ResNet is its unique residual block design, where each block contains two one-dimensional convolutional layers separated by batch normalization and ReLU activation functions. The residual blocks use skip connections to directly add the input to the output. If the input and output dimensions do not match, the shortcut connection adjusts the dimensionality—as represented by the dashed line process in Figure A2c—to ensure continuity of the information flow. If the dimensions match, the input is simply added directly to the output without adjustment, as shown by the solid line in Figure A2c. This approach not only enhances the model’s expressive power but also improves its generalization performance, making it highly suitable for datasets with complex patterns and structures. As shown in Figure A2c, the specific structure of ResNet begins with a 1D-convolutional operation with 16 output channels, followed by batch normalization and ReLU activation. The network then consists of four stages, each containing two residual blocks, with channel numbers increasing progressively to 16, 32, 64, and 128.
To further illustrate the rationality of our use of the network, under the condition of C n 2 = 1 × 10 13   m 2 / 3 and l = 3, we used 400 sets of echo OAM spectral data (four targets, 100 sets for each target) to verify the accuracy of the model. We gradually increased the number of layers of the model from the relatively simple MLP, as shown in Table A1, and found that the recognition performance of the MLP showed significant improvement with the increase in the number of fully connected layers. We can see CNN achieves high recognition accuracy with a lightweight architecture comprising merely two convolutional layers (each followed by pooling operations). In contrast, an MLP requires a complex structure with multiple fully connected layers (with 128-256-512-256-128 neurons, respectively) to achieve comparable performance. Moreover, we varied the number of residual blocks, as shown in Figure A2 and Table A1, and gradually increased the ResNet residuals, finding that the recognition rate improved with the increase in residuals. Thus, we finally choose ResNet18.
It is worth noting that although CNN’s recognition rate is slightly lower in the case of strong atmospheric turbulence ( C n 2 = 1 × 10 13   m 2 / 3 ), the training time of CNN is much lower than that of MLP and ResNet, as is shown in Table A2.
Figure A2. The structure of the three networks (a) MLP; (b) CNN; (c) ResNet 18.
Figure A2. The structure of the three networks (a) MLP; (b) CNN; (c) ResNet 18.
Photonics 12 00771 g0a2
Table A1. The recognition rates of three neural networks under different layers of MLP and ResNet when l = 3 and turbulence intensity is C n 2 = 1 × 10 13   m 2 / 3 .
Table A1. The recognition rates of three neural networks under different layers of MLP and ResNet when l = 3 and turbulence intensity is C n 2 = 1 × 10 13   m 2 / 3 .
(a) MLP
LayersAccuracy (%)Time (s)
21-128-477.522
21-128-256-128-486.25126
21-128-256-512-256-128-492332
(b) ResNet
The retained residual block numberAccuracy (%)Time (s)
Block 1,292.5152
Block 1,2,393.75226
Block 1,2,3,4(ResNet18)95.5476
Table A2. The recognition rates of three proposed neural networks under different layers of MLP and ResNet when l = 3 and turbulence intensity is C n 2 = 1 × 10 13   m 2 / 3 .
Table A2. The recognition rates of three proposed neural networks under different layers of MLP and ResNet when l = 3 and turbulence intensity is C n 2 = 1 × 10 13   m 2 / 3 .
NetworkAccuracy (%)Time (s)
MLP92332
CNN90.7596
ResNet95.5476
To provide a comprehensive comparison and highlight the significance of our proposed method, we have included a detailed comparison table with the GS algorithm in [14] when C n 2 = 1 × 10 13   m 2 / 3 and l = 3. Below is a summary of the comparison.
Table A3. The recognition performance comparison when C n 2 = 1 × 10 13   m 2 / 3 and l = 3.
Table A3. The recognition performance comparison when C n 2 = 1 × 10 13   m 2 / 3 and l = 3.
MethodAccuracy (%)Notes
Random Guessing25Baseline for random selection among four categories.
Simpler Classifier (21-10-4)71.5Average performance using simpler classifiers on the same dataset.
GS Algorithm in [14]88High recognition rate but suffers from high computational demands and real-time adaptation issues.
Proposed MLP92Optimal configuration with high recognition rate and medium computational cost.
Proposed CNN90.75Most efficient processing of spatially structured data like OAM spectra in three proposed models.
Proposed ResNet95.5Deep network structure with residual blocks, offering superior performance and stability under strong turbulence and increasing of target size.
These results demonstrate that our proposed models not only outperform traditional methods and simpler classifiers but also offer comparable or superior performance to the GS algorithm while requiring fewer computational resources.

References

  1. Lian, Y.; Qi, X.; Wang, Y.; Bai, Z.; Wang, Y.; Lu, Z. Oam Beam Generation in Space and Its Applications: A Review. Opt. Lasers Eng. 2022, 151, 106923. [Google Scholar] [CrossRef]
  2. Li, M.; Yan, S.; Zhang, Y.; Zhou, Y.; Yao, B. Orbital Angular Momentum in Optical Manipulations. J. Opt. 2022, 24, 114001. [Google Scholar] [CrossRef]
  3. Padgett, M.; Bowman, R. Tweezers with a Twist. Nat. Photonics 2011, 5, 343–348. [Google Scholar] [CrossRef]
  4. Bacco, D.; Cozzolino, D.; Da Lio, B.; Ding, Y.; Rottwitt, K.; Oxenløwe, L.K. Quantum Communication with Orbital Angular Momentum. In Proceedings of the 2020 22nd International Conference on Transparent Optical Networks (ICTON) 2020, Bari, Italy, 19–23 July 2020. [Google Scholar]
  5. Zhongyi, G.; Chaofan, G.; Hongjun, L.; Jingjing, L.; Zikun, W.; Yang, Y.; Yubin, G. Research Advances of Orbital Angular Momentum Based Optical Communication Technology. Opto-Electron. Eng. 2020, 47, 190593–1-93-34. [Google Scholar]
  6. Liu, K.; Cheng, Y.; Liu, H.; Wang, H. Computational Imaging with Low-Order Oam Beams at Microwave Frequencies. Sci. Rep. 2020, 10, 11641. [Google Scholar] [CrossRef]
  7. Hu, Y.; Zhang, M.; Dou, J.; Zhao, J.; Li, B. Influences of Salinity and Temperature on Propagation of Radially Polarized Rotationally-Symmetric Power-Exponent-Phase Vortex Beams in Oceanic Turbulence. Opt. Express 2022, 30, 42772–42783. [Google Scholar] [CrossRef] [PubMed]
  8. Pan, Y.; Zhao, M.; Zhang, M.; Dou, J.; Zhao, J.; Li, B.; Hu, Y. Propagation Properties of Rotationally-Symmetric Power-Exponent-Phase Vortex Beam through Oceanic Turbulence. Opt. Laser Technol. 2022, 159, 109024. [Google Scholar] [CrossRef]
  9. Huang, G.; Geng, C.; Li, F.; Yang, Y.; Li, X. Adaptive Smf Coupling Based on Precise-Delayed Spgd Algorithm and Its Application in Free Space Optical Communication. IEEE Photonics J. 2018, 10, 1–12. [Google Scholar] [CrossRef]
  10. Riesgo, F.G.; Gómez, S.L.S.; Rodríguez, J.D.S.; Gutiérrez, C.G.; Hernando, Y.M.; Martínez, L.M.M.; Ramos, A.A.; Vera, M.C.; Cagigal, M.N.; Juez, F.J.D.C. Comparative Study of Shack-Hartmann Configurations for Atmospheric Turbulence Reconstructions in Solar Adaptive Optics. Opt. Lasers Eng. 2022, 158, 107157. [Google Scholar] [CrossRef]
  11. Fu, S.; Wang, T.; Zhang, S.; Zhang, Z.; Zhai, Y.; Gao, C. Non-Probe Compensation of Optical Vortices Carrying Orbital Angular Momentum. Photonics Res. 2017, 5, 251–255. [Google Scholar] [CrossRef]
  12. Li, S.; Chen, S.; Gao, C.; Willner, A.E.; Wang, J. Atmospheric Turbulence Compensation in Orbital Angular Momentum Communications: Advances and Perspectives. Opt. Commun. 2018, 408, 68–81. [Google Scholar] [CrossRef]
  13. Zhao, H.; Deng, W.; Li, J.; Ma, W. Modified Gerchberg-Saxton algorithm-based probe-free wavefront distortion compensation of an OAM beam. Optik 2022, 269, 169816. [Google Scholar] [CrossRef]
  14. Cui, C.; Wang, H.; Zhang, Z.; Lin, R.; Yun, H.; Lv, X.; Song, J.; Feng, R.; Zhao, Y. Enhancing Target Recognition Rate in Atmospheric Turbulence Using Orbital Angular Momentum Spectra of Vortex Beams. Phys. Scr. 2024, 99, 125514. [Google Scholar] [CrossRef]
  15. Zhao, J.; Zhang, Z.; Li, Y.; Cen, L. Multidimensional Information Assisted Deep Learning Realizing Flexible Recognition of Vortex Beam Modes. IEEE Photonics J. 2021, 13, 1–6. [Google Scholar] [CrossRef]
  16. Zhou, S.; Li, L.; Gao, C.; Fu, S. Deep-Learning Assisted Fast Orbital Angular Momentum Complex Spectrum Analysis. Opt. Lett. 2023, 49, 173–176. [Google Scholar] [CrossRef]
  17. Xiong, W.; Luo, Y.; Liu, J.; Huang, Z.; Wang, P.; Zhao, G.; Li, Y.; Gao, Y.; Chen, S.; Fan, D. Convolutional Neural Network Assisted Optical Orbital Angular Momentum Identification of Vortex Beams. IEEE Access 2020, 8, 193801–193812. [Google Scholar] [CrossRef]
  18. Wang, Z.; Dedo, M.I.; Guo, K.; Zhou, K.; Shen, F.; Sun, Y.; Liu, S.; Guo, Z. Efficient Recognition of the Propagated Orbital Angular Momentum Modes in Turbulences with the Convolutional Neural Network. IEEE Photonics J. 2019, 11, 1–14. [Google Scholar] [CrossRef]
  19. Zhang, Y.; Zhao, H.; Wu, H.; Chen, Z.; Pu, J. Recognition of Orbital Angular Momentum of Vortex Beams Based on Convolutional Neural Network and Multi-Objective Classifier. Photonics 2023, 10, 631. [Google Scholar] [CrossRef]
  20. Murtagh, F. Multilayer Perceptrons for Classification and Regression. Neurocomputing 1991, 2, 183–197. [Google Scholar] [CrossRef]
  21. He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
  22. Ruffato, G.; Massari, M.; Romanato, F. Generation of High-Order Laguerre–Gaussian Modes by Means of Spiral Phase Plates. Opt. Lett. 2014, 39, 5094–5097. [Google Scholar] [CrossRef]
  23. Yang, Y.; Li, Y.; Wang, C. Generation and Expansion of Laguerre–Gaussian Beams. J. Opt. 2022, 51, 910–926. [Google Scholar] [CrossRef]
  24. Heckenberg, N.R.; McDuff, R.; Smith, C.P.; White, A.G. Generation of Optical Phase Singularities by Computer-Generated Holograms. Opt. Lett. 1992, 17, 221–223. [Google Scholar] [CrossRef] [PubMed]
  25. Qiu, S.; Ding, Y.; Liu, T.; Liu, Z.; Wu, H.; Ren, Y. Fragmental Optical Vortex for the Detection of Rotating Object Based on the Rotational Doppler Effect. Opt. Express 2022, 30, 47350–47360. [Google Scholar] [CrossRef]
  26. Bouchal, Z.; Celechovský, R. Mixed Vortex States of Light as Information Carriers. New J. Phys. 2004, 6, 131. [Google Scholar] [CrossRef]
  27. Lin, J.; Yuan, X.-C.; Tao, S.H.; Burge, R.E. Collinear Superposition of Multiple Helical Beams Generated by a Single Azimuthally Modulated Phase-Only Element. Opt. Lett. 2005, 30, 3266–3268. [Google Scholar] [CrossRef]
  28. Liu, X.; Huang, S.; Xie, W.; Pei, Z. Topological Charge Parallel Measurement Method for Optical Vortices Based on Computer-Generated Holography. J. Opt. Technol. 2022, 89, 94–100. [Google Scholar] [CrossRef]
  29. Lin, J.; Yuan, X.; Tao, S.H.; Burge, R.E. Synthesis of Multiple Collinear Helical Modes Generated by a Phase-Only Element. JOSA A 2006, 23, 1214–1218. [Google Scholar] [CrossRef]
  30. Li, Y.; Yu, L.; Zhang, Y. Influence of Anisotropic Turbulence on the Orbital Angular Momentum Modes of Hermite-Gaussian Vortex Beam in the Ocean. Opt. Express 2017, 25, 12203–12215. [Google Scholar] [CrossRef] [PubMed]
  31. Fu, S.; Gao, C. Influences of Atmospheric Turbulence Effects on the Orbital Angular Momentum Spectra of Vortex Beams. Photonics Res. 2016, 4, B1–B4. [Google Scholar] [CrossRef]
  32. Tatarski, V.I. Wave Propagation in a Turbulent Medium; Courier Dover Publications: Mineola, NY, USA, 2016. [Google Scholar]
  33. Shirazi, M.I.; Khatir, S.; Boutchicha, D.; Wahab, M.A. Feature Extraction and Classification of Multiple Cracks from Raw Vibrational Responses of Composite Beams Using 1d-Cnn Network. Compos. Struct. 2023, 327, 117701. [Google Scholar] [CrossRef]
  34. Dai, Q.; Luo, Z.; Li, Z.; Lyu, S.; Xue, X.; Song, S.; Yu, S.; Huang, Y. Field-Based, Non-Destructive, and Rapid Detection of Pesticide Residues on Kumquat (Citrus Japonica) Surfaces Using Handheld Spectrometer and 1d-Resnet. Agronomy 2025, 15, 625. [Google Scholar] [CrossRef]
Figure 1. Schematic diagram of the optical system for measuring the OAM spectrum of a target. P: polarizer; SMF: single-mode fiber; SLM: spatial light modulator; CCD: charge-coupled device; BS: beam splitter; M: mirror; L: lens.
Figure 1. Schematic diagram of the optical system for measuring the OAM spectrum of a target. P: polarizer; SMF: single-mode fiber; SLM: spatial light modulator; CCD: charge-coupled device; BS: beam splitter; M: mirror; L: lens.
Photonics 12 00771 g001
Figure 2. (ad) Schematic diagram of the emitted vortex beam being reflected by four targets. (eh) Four target echo light fields. (i) OAM spectra of the echo signals from triangular, square, and pentagonal targets.
Figure 2. (ad) Schematic diagram of the emitted vortex beam being reflected by four targets. (eh) Four target echo light fields. (i) OAM spectra of the echo signals from triangular, square, and pentagonal targets.
Photonics 12 00771 g002
Figure 3. OAM spectra of echo signals from triangular targets with emitted topological charges of (a) 4, (b) ±4 superposition, (c) 1, 3, and 5 superposition when there is no turbulence.
Figure 3. OAM spectra of echo signals from triangular targets with emitted topological charges of (a) 4, (b) ±4 superposition, (c) 1, 3, and 5 superposition when there is no turbulence.
Photonics 12 00771 g003
Figure 4. Training loss, test loss curves for training three networks using OAM spectral data when C n 2 = 1 × 10 14   m 2 / 3 .
Figure 4. Training loss, test loss curves for training three networks using OAM spectral data when C n 2 = 1 × 10 14   m 2 / 3 .
Photonics 12 00771 g004
Figure 5. Curves of target recognition rates of the three neural networks varying with atmospheric turbulence intensity when the emitted topological charge l = 3.
Figure 5. Curves of target recognition rates of the three neural networks varying with atmospheric turbulence intensity when the emitted topological charge l = 3.
Photonics 12 00771 g005
Figure 6. Confusion matrices of CNN, MLP, and ResNet for OAM spectrum recognition of four targets under four turbulence intensities, where T is a triangle, S is a square, P is a pentagon, and C is a circle.
Figure 6. Confusion matrices of CNN, MLP, and ResNet for OAM spectrum recognition of four targets under four turbulence intensities, where T is a triangle, S is a square, P is a pentagon, and C is a circle.
Photonics 12 00771 g006
Figure 7. (a) Curves of three targets’ relative power of −1-order dispersion characteristic varying with topological charges of emitted beam in the absence of turbulence; (b) curves of the −1-order dispersion characteristics of the echo signal varying with target size, for a pentagonal target illuminated by vortex beams with different topological charges in the absence of turbulence.
Figure 7. (a) Curves of three targets’ relative power of −1-order dispersion characteristic varying with topological charges of emitted beam in the absence of turbulence; (b) curves of the −1-order dispersion characteristics of the echo signal varying with target size, for a pentagonal target illuminated by vortex beams with different topological charges in the absence of turbulence.
Photonics 12 00771 g007
Figure 8. Curves of the three neural networks’ recognition rates varying with the topological charge of the emission vortex beam when C n 2 = 1 × 10 13   m 2 / 3 .
Figure 8. Curves of the three neural networks’ recognition rates varying with the topological charge of the emission vortex beam when C n 2 = 1 × 10 13   m 2 / 3 .
Photonics 12 00771 g008
Figure 9. The recognition rate matrices of CNN, MlP and ResNet for four targets under different atmospheric turbulence when the topological charges of the emitted beam are 1, 5, 7, where T is a triangle, S is a square, P is a pentagon and C is a circle.
Figure 9. The recognition rate matrices of CNN, MlP and ResNet for four targets under different atmospheric turbulence when the topological charges of the emitted beam are 1, 5, 7, where T is a triangle, S is a square, P is a pentagon and C is a circle.
Photonics 12 00771 g009
Figure 10. (a) Curves of three network recognition rates varying with target size η ; (b) curves of relative power of three targets’ −1-order dispersion characteristics varying with target size η .
Figure 10. (a) Curves of three network recognition rates varying with target size η ; (b) curves of relative power of three targets’ −1-order dispersion characteristics varying with target size η .
Photonics 12 00771 g010
Table 1. Recognition rates of three kinds of emitted beams when C n 2 = 1 × 10 13   m 2 / 3 .
Table 1. Recognition rates of three kinds of emitted beams when C n 2 = 1 × 10 13   m 2 / 3 .
Networkl = 4l = ±4l = 1, 3, 5
CNN93.25%88%76%
MLP96%86.5%71.75%
ResNet96%93%80.5%
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Chen, G.; Wang, H.; Yun, H.; Shi, Z.; Zhang, Z.; Cui, C.; Wu, D.; Lyu, X.; Zhao, Y. Research on Enhancing Target Recognition Rate Based on Orbital Angular Momentum Spectrum with Assistance of Neural Network. Photonics 2025, 12, 771. https://doi.org/10.3390/photonics12080771

AMA Style

Chen G, Wang H, Yun H, Shi Z, Zhang Z, Cui C, Wu D, Lyu X, Zhao Y. Research on Enhancing Target Recognition Rate Based on Orbital Angular Momentum Spectrum with Assistance of Neural Network. Photonics. 2025; 12(8):771. https://doi.org/10.3390/photonics12080771

Chicago/Turabian Style

Chen, Guanxu, Hongyang Wang, Hao Yun, Zhanpeng Shi, Zijing Zhang, Chengshuai Cui, Di Wu, Xinran Lyu, and Yuan Zhao. 2025. "Research on Enhancing Target Recognition Rate Based on Orbital Angular Momentum Spectrum with Assistance of Neural Network" Photonics 12, no. 8: 771. https://doi.org/10.3390/photonics12080771

APA Style

Chen, G., Wang, H., Yun, H., Shi, Z., Zhang, Z., Cui, C., Wu, D., Lyu, X., & Zhao, Y. (2025). Research on Enhancing Target Recognition Rate Based on Orbital Angular Momentum Spectrum with Assistance of Neural Network. Photonics, 12(8), 771. https://doi.org/10.3390/photonics12080771

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop