Abstract
We present a framework for representing and matching multi-scale, qualitative feature hierarchies. The coarse shape of an ob ject is captured by a set of blobs and ridges, representing compact and elon- gated parts of an ob ject. These parts, in turn, map to nodes in a directed acyclic graph, in which parent/child edges represent feature overlap, sib- ling edges join nodes with shared parents, and all edges encode geometric relations between the features. Given two feature hierarchies, represented as directed acyclic graphs, we present an algorithm for computing both similarity and node correspondence in the presence of noise and occlu- sion. Similarity, in turn, is a function of structural similarity, contextual similarity (geometric relations among neighboring nodes), and node con- tents similarity. Moreover, the weights of these components can be varied on a node by node basis, allowing a graph-based model to efiectively pa- rameterize the saliency of its constraints. We demonstrate the approach on two domains: gesture recognition and face detection.