Abstract | ||
---|---|---|
In this paper, a novel affine invariant shape descriptor for planar contours is proposed. It is based on a multi-resolution representation of the contour. For each contour resolution, a shape signature is defined from the contour points and the initial contour centroid and points. Finally, Fourier descriptors are computed for each signature. The proposed descriptor is invariant to affine transformations. Experiments carried on the MPEG-7 coutour database and the Multiview Curve Dataset (MCD) show that our proposed descriptor outperforms other contour shape descriptors proposed in the literature. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-23234-8_46 | IMAGE ANALYSIS AND PROCESSING - ICIAP 2015, PT II |
Field | DocType | Volume |
Affine transformation,Shape signature,Computer vision,Affine shape adaptation,Pattern recognition,Computer science,Fourier transform,Affine invariant,Planar,Invariant (mathematics),Artificial intelligence,Centroid | Conference | 9280 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taha Faidi | 1 | 0 | 0.34 |
Faten Chaieb | 2 | 27 | 5.23 |
Faouzi Ghorbel | 3 | 361 | 46.48 |