Trade-off Between Spatial and Angular Resolution in Facial Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909102208188416 |
|---|---|
| author | Alam, Muhammad Zeshan kelowani, Sousso Elsaeidy, Mohamed |
| author_facet | Alam, Muhammad Zeshan kelowani, Sousso Elsaeidy, Mohamed |
| contents | Ensuring robustness in face recognition systems across various challenging conditions is crucial for their versatility. State-of-the-art methods often incorporate additional information, such as depth, thermal, or angular data, to enhance performance. However, light field-based face recognition approaches that leverage angular information face computational limitations. This paper investigates the fundamental trade-off between spatio-angular resolution in light field representation to achieve improved face recognition performance. By utilizing macro-pixels with varying angular resolutions while maintaining the overall image size, we aim to quantify the impact of angular information at the expense of spatial resolution, while considering computational constraints. Our experimental results demonstrate a notable performance improvement in face recognition systems by increasing the angular resolution, up to a certain extent, at the cost of spatial resolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07263 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Trade-off Between Spatial and Angular Resolution in Facial Recognition Alam, Muhammad Zeshan kelowani, Sousso Elsaeidy, Mohamed Computer Vision and Pattern Recognition Ensuring robustness in face recognition systems across various challenging conditions is crucial for their versatility. State-of-the-art methods often incorporate additional information, such as depth, thermal, or angular data, to enhance performance. However, light field-based face recognition approaches that leverage angular information face computational limitations. This paper investigates the fundamental trade-off between spatio-angular resolution in light field representation to achieve improved face recognition performance. By utilizing macro-pixels with varying angular resolutions while maintaining the overall image size, we aim to quantify the impact of angular information at the expense of spatial resolution, while considering computational constraints. Our experimental results demonstrate a notable performance improvement in face recognition systems by increasing the angular resolution, up to a certain extent, at the cost of spatial resolution. |
| title | Trade-off Between Spatial and Angular Resolution in Facial Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.07263 |