Name
Abstract | ||
|---|---|---|
This paper presents an affine invariant shape descriptor which could be applied to both binary and gray-level images. The proposed algorithm uses gradient based features which are extracted along the object boundaries. We use two-dimensional steerable G-Filters [1] to obtain gradient information at different orientations. We aggregate the gradients into a shape signature. The signatures derived from rotated objects are shifted versions of the signatures derived from the original object. The shape descriptor is defined as the Fourier transform of the signature. We also provide a distance definition for the proposed descriptor taking shifted property of the signature into account. The performance of the proposed descriptor is evaluated over a database containing license plate characters. The experiments show that the devised method outperforms other well-known Fourier-based shape descriptors such as centroid distance and boundary curvature. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1007/11848035_68 | MRCS |
Keywords | Field | DocType |
affine invariant gradient,proposed descriptor,distance definition,well-known fourier-based shape,object boundary,shape descriptor,gradient information,centroid distance,proposed algorithm,shape signature,affine invariant shape descriptor | Affine transformation,Computer vision,Search algorithm,Curvature,Computer science,Binary image,Fourier transform,Invariant (mathematics),Artificial intelligence,Centroid,Binary number | Conference |
Volume | ISSN | ISBN |
4105 | 0302-9743 | 3-540-39392-7 |
Citations | PageRank | References |
4 | 0.44 | 12 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Abdulkerim Çapar | 1 | 19 | 4.28 |
| Binnur Kurt | 2 | 39 | 3.49 |
| Muhittin Gökmen | 3 | 137 | 16.12 |