Classification of Holograms with 3D-CNN
A hologram, measured by using appropriate coherent illumination, records all substantial volumetric information of the measured sample. It is encoded in its interference patterns and, from these, the image of the sample objects can be reconstructed in different depths by using standard techniques of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/21/8366 |
| _version_ | 1797466497069613056 |
|---|---|
| author | Dániel Terbe László Orzó Ákos Zarándy |
| author_facet | Dániel Terbe László Orzó Ákos Zarándy |
| author_sort | Dániel Terbe |
| collection | DOAJ |
| description | A hologram, measured by using appropriate coherent illumination, records all substantial volumetric information of the measured sample. It is encoded in its interference patterns and, from these, the image of the sample objects can be reconstructed in different depths by using standard techniques of digital holography. We claim that a 2D convolutional network (CNN) cannot be efficient in decoding this volumetric information spread across the whole image as it inherently operates on local spatial features. Therefore, we propose a method, where we extract the volumetric information of the hologram by mapping it to a volume—using a standard wavefield propagation algorithm—and then feed it to a 3D-CNN-based architecture. We apply this method to a challenging real-life classification problem and compare its performance with an equivalent 2D-CNN counterpart. Furthermore, we inspect the robustness of the methods to slightly defocused inputs and find that the 3D method is inherently more robust in such cases. Additionally, we introduce a hologram-specific augmentation technique, called hologram defocus augmentation, that improves the performance of both methods for slightly defocused inputs. The proposed 3D-model outperforms the standard 2D method in classification accuracy both for in-focus and defocused input samples. Our results confirm and support our fundamental hypothesis that a 2D-CNN-based architecture is limited in the extraction of volumetric information globally encoded in the reconstructed hologram image. |
| first_indexed | 2024-03-09T18:40:37Z |
| format | Article |
| id | doaj.art-f355521e24ad4104bb2cbcfc7a606e2f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:40:37Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f355521e24ad4104bb2cbcfc7a606e2f2023-11-24T06:46:56ZengMDPI AGSensors1424-82202022-10-012221836610.3390/s22218366Classification of Holograms with 3D-CNNDániel Terbe0László Orzó1Ákos Zarándy2Institute for Computer Science and Control, H-1111 Budapest, HungaryInstitute for Computer Science and Control, H-1111 Budapest, HungaryInstitute for Computer Science and Control, H-1111 Budapest, HungaryA hologram, measured by using appropriate coherent illumination, records all substantial volumetric information of the measured sample. It is encoded in its interference patterns and, from these, the image of the sample objects can be reconstructed in different depths by using standard techniques of digital holography. We claim that a 2D convolutional network (CNN) cannot be efficient in decoding this volumetric information spread across the whole image as it inherently operates on local spatial features. Therefore, we propose a method, where we extract the volumetric information of the hologram by mapping it to a volume—using a standard wavefield propagation algorithm—and then feed it to a 3D-CNN-based architecture. We apply this method to a challenging real-life classification problem and compare its performance with an equivalent 2D-CNN counterpart. Furthermore, we inspect the robustness of the methods to slightly defocused inputs and find that the 3D method is inherently more robust in such cases. Additionally, we introduce a hologram-specific augmentation technique, called hologram defocus augmentation, that improves the performance of both methods for slightly defocused inputs. The proposed 3D-model outperforms the standard 2D method in classification accuracy both for in-focus and defocused input samples. Our results confirm and support our fundamental hypothesis that a 2D-CNN-based architecture is limited in the extraction of volumetric information globally encoded in the reconstructed hologram image.https://www.mdpi.com/1424-8220/22/21/8366digital holographyCNN3D-CNNneural networksdeep learning |
| spellingShingle | Dániel Terbe László Orzó Ákos Zarándy Classification of Holograms with 3D-CNN Sensors digital holography CNN 3D-CNN neural networks deep learning |
| title | Classification of Holograms with 3D-CNN |
| title_full | Classification of Holograms with 3D-CNN |
| title_fullStr | Classification of Holograms with 3D-CNN |
| title_full_unstemmed | Classification of Holograms with 3D-CNN |
| title_short | Classification of Holograms with 3D-CNN |
| title_sort | classification of holograms with 3d cnn |
| topic | digital holography CNN 3D-CNN neural networks deep learning |
| url | https://www.mdpi.com/1424-8220/22/21/8366 |
| work_keys_str_mv | AT danielterbe classificationofhologramswith3dcnn AT laszloorzo classificationofhologramswith3dcnn AT akoszarandy classificationofhologramswith3dcnn |