Abstract | ||
---|---|---|
In this paper, we present the use of Full-Zernike moments as a local characterization of the image signal. Their computation allows us to construct a locally invariant vector, of which the projection in an index table provides a vote for some model-image. This approach is based on the quasi-invariant theory applied to perspective transformation. Then it requires a characterization being invariant to translation, rotation and change of scale in the image; in other respect, an appropriate normalization of the signal delivers invariance to illuminance conditions. |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/ICPR.2000.905644 | ICPR |
Keywords | Field | DocType |
local characterization,perspective transformation,index table,appropriate normalization,full-zernike moment,invariant vector,invariant local vector,image signal,quasi-invariant theory,content-based image,computer vision,image reconstruction,vectors,invariant theory,indexing,voting,scale invariance,image retrieval,indexation,polynomials | Computer vision,Normalization (statistics),Invariant (physics),Pattern recognition,Image texture,Computer science,Image retrieval,Invariant (mathematics),Artificial intelligence,Image moment,Content-based image retrieval,Visual Word | Conference |
ISSN | Citations | PageRank |
1051-4651 | 1 | 0.41 |
References | Authors | |
7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Erwan Bigorgne | 1 | 21 | 3.89 |
Catherine Achard | 2 | 158 | 19.60 |
Jean Devars | 3 | 31 | 5.61 |