Name
Abstract | ||
|---|---|---|
Similarity computation of images is a crucial process in image analysis, aiming at detecting changes in real world images taken at different times, for example. Traditional intensity-based methods lead to satisfactory results in different situations but fail in others when dealing with high local structural variations. In this paper, a tensor-based metric for dissimilarity estimation is proposed, taking into account the local structural information of the underlying images. Results show that using the proposed metric, relevant local patterns' dissimilarities can be better detected comparing to the intensity-based metric, thus improving the analysis of images in different applications such as medical imaging, for example. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/IWSSIP.2018.8439205 | 2018 25th International Conference on Systems, Signals and Image Processing (IWSSIP) |
Keywords | Field | DocType |
Gradient fields,Image analysis,Local structures,Similarity,Structure tensor | Computer vision,Similarity computation,Similarity measure,Tensor,Pattern recognition,Medical imaging,Computer science,Artificial intelligence,Structure tensor | Conference |
ISSN | ISBN | Citations |
2157-8672 | 978-1-5386-6980-8 | 0 |
PageRank | References | Authors |
0.34 | 7 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Adib Akl | 1 | 25 | 5.33 |
| Charles Yaacoub | 2 | 83 | 14.28 |