Computer Vision, IEEE International Conference on (2005)
Oct. 17, 2005 to Oct. 20, 2005
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.2005.71
V. Shiv Naga Prasad , University of Maryland - College Park
Larry S. Davis , University of Maryland - College Park
We present an algorithm for detecting multiple rotational symmetries in natural images. Given an image, its gradient magnitude field is computed, and information from the gradients is spread using a diffusion process in the form of a Gradient Vector Flow (GVF) field. We construct a graph whose nodes correspond to pixels in the image, connecting points that are likely to be rotated versions of one another. The n-cycles present in the graph are made to vote for C_n symmetries, their votes being weighted by the errors in transformation between GVF in the neighborhood of the voting points, and the irregularity of the n-sided polygons formed by the voters. The votes are accumulated at the centroids of possible rotational symmetries, generating a confidence map for each order of symmetry. We tested the method with several natural images.
L. S. Davis and V. S. Prasad, "Detecting Rotational Symmetries," Computer Vision, IEEE International Conference on(ICCV), Beijing, China, 2005, pp. 954-961.