Measuring laser beams with a neural network
A deep neural network (NN) is used to simultaneously detect laser beams in images and measure their center coordinates, radii, and angular orientations. A dataset of images containing simulated laser beams and a dataset of images with experimental laser beams—generated using a spatial light modulato...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Optica Publishing Group
2022
|
| _version_ | 1797108935495254016 |
|---|---|
| author | Hofer, LR Krstajic, M Smith, RP |
| author_facet | Hofer, LR Krstajic, M Smith, RP |
| author_sort | Hofer, LR |
| collection | OXFORD |
| description | A deep neural network (NN) is used to simultaneously detect laser beams in images and measure their center coordinates, radii, and angular orientations. A dataset of images containing simulated laser beams and a dataset of images with experimental laser beams—generated using a spatial light modulator—are used to train and evaluate the NN. After training on the simulated dataset the NN achieves beam parameter root mean square errors (RMSEs) of less than 3.4% on the experimental dataset. Subsequent training on the experimental dataset causes the RMSEs to fall below 1.1%. The NN method can be used as a stand-alone measurement of the beam parameters or can compliment other beam profiling methods by providing an accurate region-of-interest.
|
| first_indexed | 2024-03-07T07:35:00Z |
| format | Journal article |
| id | oxford-uuid:7a26db34-2704-43c8-ae83-d4bf1e5ec658 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:35:00Z |
| publishDate | 2022 |
| publisher | Optica Publishing Group |
| record_format | dspace |
| spelling | oxford-uuid:7a26db34-2704-43c8-ae83-d4bf1e5ec6582023-03-02T10:19:25ZMeasuring laser beams with a neural networkJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:7a26db34-2704-43c8-ae83-d4bf1e5ec658EnglishSymplectic ElementsOptica Publishing Group2022Hofer, LRKrstajic, MSmith, RPA deep neural network (NN) is used to simultaneously detect laser beams in images and measure their center coordinates, radii, and angular orientations. A dataset of images containing simulated laser beams and a dataset of images with experimental laser beams—generated using a spatial light modulator—are used to train and evaluate the NN. After training on the simulated dataset the NN achieves beam parameter root mean square errors (RMSEs) of less than 3.4% on the experimental dataset. Subsequent training on the experimental dataset causes the RMSEs to fall below 1.1%. The NN method can be used as a stand-alone measurement of the beam parameters or can compliment other beam profiling methods by providing an accurate region-of-interest. |
| spellingShingle | Hofer, LR Krstajic, M Smith, RP Measuring laser beams with a neural network |
| title | Measuring laser beams with a neural network |
| title_full | Measuring laser beams with a neural network |
| title_fullStr | Measuring laser beams with a neural network |
| title_full_unstemmed | Measuring laser beams with a neural network |
| title_short | Measuring laser beams with a neural network |
| title_sort | measuring laser beams with a neural network |
| work_keys_str_mv | AT hoferlr measuringlaserbeamswithaneuralnetwork AT krstajicm measuringlaserbeamswithaneuralnetwork AT smithrp measuringlaserbeamswithaneuralnetwork |