Scale invariant sillhouette features

In this study, a feature extractor and a global descriptor for closed planar curves, i.e. silhouettes, are proposed. Initially, the closed curve is arc-length sampled and the Gaussian scale-space is constructed. Using the absolute curvature values and orientations of the curves within the higher scale levels, scale invariant features are obtained. These features are transformed into a global descriptor, namely the feature images, and shape recognition is performed. The proposed method is evaluated using a ship silhouette image set and the results show good success rates with low computation burden.