Y. Ebrahim, W. Abdelsalam, M. Ahmed, and S.-C. Chau (Canada)
Shape representation, Shape matching, Hilbert curve, Wavelet transform
In this paper we present a novel approach to shape representation and matching based on the combination of the Hilbert space filling curve and Wavelet analysis. Our objective is to introduce a robust technique that capitalizes on the localization-preserving nature of the Hilbert space filling curve and the approximation capabilities of the Wavelet transform. Our technique produces a concise 1D representation of the image that can be used to search an image database for a match either for the whole image or a part of it. The technique exhibited robustness in cases of partial and occluded image matching. Our technique is translation, scale, and stretching invariant. It works well on many types of shapes including those that were traditionally either contour- or region-based oriented. We present some experimental results on the MPEG-7 dataset.
Important Links:
Go Back
