Demons registration for 2D empirical wavelet transforms
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912127516672000 |
|---|---|
| author | Lucas, Charles-Gérard Gilles, Jérôme |
| author_facet | Lucas, Charles-Gérard Gilles, Jérôme |
| contents | The empirical wavelet transform is a fully adaptive time-scale representation that has been widely used in the last decade. Inspired by the empirical mode decomposition, it consists of filter banks based on harmonic mode supports. Recently, it has been generalized to build the filter banks from any generating function using mappings. In practice, the harmonic mode supports can have low constrained shape in 2D, leading to numerical difficulties to compute the mappings and therefore the related wavelet filters. This work aims to propose an efficient numerical scheme to compute empirical wavelet coefficients using the demons registration algorithm. Results show that the proposed approach gives a numerically robust wavelet transform. An application to texture segmentation of scanning tunnelling microscope images is also presented. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13075 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Demons registration for 2D empirical wavelet transforms Lucas, Charles-Gérard Gilles, Jérôme Image and Video Processing The empirical wavelet transform is a fully adaptive time-scale representation that has been widely used in the last decade. Inspired by the empirical mode decomposition, it consists of filter banks based on harmonic mode supports. Recently, it has been generalized to build the filter banks from any generating function using mappings. In practice, the harmonic mode supports can have low constrained shape in 2D, leading to numerical difficulties to compute the mappings and therefore the related wavelet filters. This work aims to propose an efficient numerical scheme to compute empirical wavelet coefficients using the demons registration algorithm. Results show that the proposed approach gives a numerically robust wavelet transform. An application to texture segmentation of scanning tunnelling microscope images is also presented. |
| title | Demons registration for 2D empirical wavelet transforms |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2409.13075 |