Abstract
We present an efficient multi stage approach to detection of deformable ob jects in real, cluttered images given a single or few hand drawn examples as models. The method handles deformations of the ob- ject by first breaking the given model into segments at high curvature points. We allow bending at these points as it has been studied that deformation typically happens at high curvature points. The broken seg- ments are then scaled, rotated, deformed and searched independently in the gradient image. Point maps are generated for each segment that rep- resent the locations of the matches for that segment. We then group k points from the point maps of k adjacent segments using a cost function that takes into account local scale variations as well as inter-segment orientations. These matched groups yield plausible locations for the ob- jects. In the fine matching stage, the entire ob ject contour in the localized regions is built from the k-segment groups and given a comprehensive score in a method that uses dynamic programming. An evaluation of our algorithm on a standard dataset yielded results that are better than pub- lished work on the same dataset. At the same time, we also evaluate our algorithm on additional images with considerable ob ject deformations to verify the robustness of our method.