Abstract
In this paper, we propose an ob ject detection/recognition al- gorithm based on a new set of shape-driven features and morphological operators. Each ob ject class is modeled by the corner points (junctions) on its contour. We design two types of shape-context like features be- tween the corner points, which are efficient to compute and effective in capturing the underlying shape deformation. In the testing stage, we use a recently proposed junction detection algorithm [1] to detect corner points/junctions on natural images. The detection and recognition of an ob ject are then done by matching learned shape features to those in the input image with an efficient search strategy. The proposed system is robust to a certain degree of scale change and we obtained encourag- ing results on the ETHZ dataset. Our algorithm also has advantages of recognizing ob ject parts and dealing with occlusions.