Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Geometric heat equation and nonlinear diffusion of shapes and images
Computer Vision and Image Understanding
| Hi-index | 0.00 |
The maxima of Curvature Scale Space (CSS) image have already been used to represent 2-D shapes in different applications. The representation has showed robustness under the similarity transformations. In this paper, we examine the performance of the representation under affine transformations. Since the CSS image employs the arc length parametrisation which is not affine invariant, we expect some deviation in the maxima of the CSS image under shear. However, we show that the locations of the maxima of the CSS image do not change dramatically even under large affine transformations. Applying transformations to every object boundary of our database of 1100 images, we construct a large database of 5500 boundary contours. The contours in the database demonstrate a great range of shape variation. The CSS representation is then used to find similar shapes from this prototype database. We observe that for this database, 95% of transformed versions of the original shapes are among the first 20 outputs of the system. This provides substantial evidence of stability of the the CSS image and its contour maxima under affine transformation.