Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty Weather
Structured light is gaining importance in free-space communication. Classifying spatially-structured light modes is challenging in a dusty environment because of the distortion on the propagating beams. This article addresses this challenge by proposing a deep learning convolutional autoencoder algo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10223284/ |
| _version_ | 1797692229020549120 |
|---|---|
| author | Ahmed B. Ibrahim Amr M. Ragheb Ahmed S. Almaiman Abderrahmen Trichili Waddah S. Saif Saleh A. Alshebeili |
| author_facet | Ahmed B. Ibrahim Amr M. Ragheb Ahmed S. Almaiman Abderrahmen Trichili Waddah S. Saif Saleh A. Alshebeili |
| author_sort | Ahmed B. Ibrahim |
| collection | DOAJ |
| description | Structured light is gaining importance in free-space communication. Classifying spatially-structured light modes is challenging in a dusty environment because of the distortion on the propagating beams. This article addresses this challenge by proposing a deep learning convolutional autoencoder algorithm for modes denoising followed by a neural network for modes classification. The input to the classifier was set to be either the denoised image or the latent code of the convolutional autoencoder. This code is a low-dimensional representation of the inputted images. The proposed machine learning (ML) models were trained and tested using laboratory-generated mode data sets from the Laguerre and Hermite Gaussian mode bases. The results show that the two proposed approaches achieve an average classification accuracy exceeding 98%, and both are better than the classification accuracy reported recently (83–91%) in the literature. |
| first_indexed | 2024-03-12T02:24:35Z |
| format | Article |
| id | doaj.art-eddb6da0075646a781d5a01c3f333026 |
| institution | Directory Open Access Journal |
| issn | 1943-0655 |
| language | English |
| last_indexed | 2024-03-12T02:24:35Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj.art-eddb6da0075646a781d5a01c3f3330262023-09-05T23:00:18ZengIEEEIEEE Photonics Journal1943-06552023-01-0115511010.1109/JPHOT.2023.330608610223284Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty WeatherAhmed B. Ibrahim0https://orcid.org/0000-0002-0485-9117Amr M. Ragheb1https://orcid.org/0000-0002-4449-0182Ahmed S. Almaiman2https://orcid.org/0000-0001-9526-8517Abderrahmen Trichili3https://orcid.org/0000-0001-8005-6319Waddah S. Saif4https://orcid.org/0000-0002-8140-8803Saleh A. Alshebeili5https://orcid.org/0000-0003-4157-9277KACST-TIC in Radio Frequency and Photonics (RFTONICS), King Saud University, Riyadh, Saudi ArabiaElectrical Engineering Department, King Saud University, Riyadh, Saudi ArabiaElectrical Engineering Department, King Saud University, Riyadh, Saudi ArabiaComputer, Electrical, and Mathematical Sciences and Engineering Department, King Abdullah University of Science and Technology, Thuwal, Saudi ArabiaDepartment of Electrical and Computer Engineering, Memorial University, St. John's, NL, CanadaElectrical Engineering Department, King Saud University, Riyadh, Saudi ArabiaStructured light is gaining importance in free-space communication. Classifying spatially-structured light modes is challenging in a dusty environment because of the distortion on the propagating beams. This article addresses this challenge by proposing a deep learning convolutional autoencoder algorithm for modes denoising followed by a neural network for modes classification. The input to the classifier was set to be either the denoised image or the latent code of the convolutional autoencoder. This code is a low-dimensional representation of the inputted images. The proposed machine learning (ML) models were trained and tested using laboratory-generated mode data sets from the Laguerre and Hermite Gaussian mode bases. The results show that the two proposed approaches achieve an average classification accuracy exceeding 98%, and both are better than the classification accuracy reported recently (83–91%) in the literature.https://ieeexplore.ieee.org/document/10223284/Structured light modes identificationdusty image denoisingdeep learning |
| spellingShingle | Ahmed B. Ibrahim Amr M. Ragheb Ahmed S. Almaiman Abderrahmen Trichili Waddah S. Saif Saleh A. Alshebeili Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty Weather IEEE Photonics Journal Structured light modes identification dusty image denoising deep learning |
| title | Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty Weather |
| title_full | Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty Weather |
| title_fullStr | Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty Weather |
| title_full_unstemmed | Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty Weather |
| title_short | Deep Learning-Based Image Denoising Approach for the Identification of Structured Light Modes in Dusty Weather |
| title_sort | deep learning based image denoising approach for the identification of structured light modes in dusty weather |
| topic | Structured light modes identification dusty image denoising deep learning |
| url | https://ieeexplore.ieee.org/document/10223284/ |
| work_keys_str_mv | AT ahmedbibrahim deeplearningbasedimagedenoisingapproachfortheidentificationofstructuredlightmodesindustyweather AT amrmragheb deeplearningbasedimagedenoisingapproachfortheidentificationofstructuredlightmodesindustyweather AT ahmedsalmaiman deeplearningbasedimagedenoisingapproachfortheidentificationofstructuredlightmodesindustyweather AT abderrahmentrichili deeplearningbasedimagedenoisingapproachfortheidentificationofstructuredlightmodesindustyweather AT waddahssaif deeplearningbasedimagedenoisingapproachfortheidentificationofstructuredlightmodesindustyweather AT salehaalshebeili deeplearningbasedimagedenoisingapproachfortheidentificationofstructuredlightmodesindustyweather |