Abstract
A relaxation labelling method was applied to match SAR images. This was done using an efficient segmentation processing chain that produces a good representation of the lines present within the SAR image. Contextual neighbourhoods for the extracted entities were established for both corner and Delaunay graphs, and a novel hierarchical approach to strengthening the constraints provided by the graph edges was presented. Results obtained revealed that by adopting a flexible approach to the establishment of local contextual neighbourhoods, the advantages of relaxation labelling can successfully be conferred to highly noise corrupted SAR images.
| Original language | English |
|---|---|
| Pages (from-to) | 60-64 |
| Number of pages | 5 |
| Journal | IEE Conference Publication |
| Issue number | 410 |
| DOIs | |
| Publication status | Published - 1 Oct 1995 |
| Event | Proceedings of the 5th International Conference on Image Processing and its Applications - Edinburgh, UK Duration: 4 Jul 1995 → 6 Jul 1995 |
ASJC Scopus subject areas
- Electrical and Electronic Engineering
Fingerprint
Dive into the research topics of 'Matching SAR images using a hierarchical constraint process'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS