Abstract
We propose a method for ob ject category localization by par- tially matching edge contours to a single shape prototype of the category. Previous work in this area either relies on piecewise contour approxima- tions, requires meaningful supervised decompositions, or matches coarse shape-based descriptions at local interest points. Our method avoids error-prone pre-processing steps by using all obtained edges in a partial contour matching setting. The matched fragments are efficiently sum- marized and aggregated to form location hypotheses. The efficiency and accuracy of our edge fragment based voting step yields high quality hy- potheses in low computation time. The experimental evaluation achieves excellent performance in the hypotheses voting stage and yields compet- itive results on challenging datasets like ETHZ and INRIA horses.