Abstract

Methods based on local, viewpoint invariant features have proven capable of recognizing ob jects in spite of viewpoint changes, oc- clusion and clutter. However, these approaches fail when these factors are too strong, due to the limited repeatability and discriminative power of the features. As additional shortcomings, the ob jects need to be rigid and only their approximate location is found. We present a novel Ob ject Recognition approach which overcomes these limitations. An initial set of feature correspondences is first generated. The method anchors on it and then gradually explores the surrounding area, trying to construct more and more matching features, increasingly farther from the initial ones. The resulting process covers the ob ject with matches, and simultaneously separates the correct matches from the wrong ones. Hence, recognition and segmentation are achieved at the same time. Only very few correct initial matches sufice for reliable recognition. The experimental results demonstrate the stronger power of the presented method in dealing with extensive clutter, dominant occlusion, large scale and viewpoint changes. Moreover non-rigid deformations are explicitly taken into account, and the approximative contours of the ob ject are produced. The approach can extend any viewpoint invariant feature extractor.