Hamiltonian streamline-guided features

Abstract

We present a new feature extraction method based on two dynamical systems induced by intensity landscape: the negative gradient system and the Hamiltonian system. Given the dynamical systems, features are extracted using the Hamiltonian streamlines. Whereas the majority of popular feature extraction methods are computed on the local gradient, our new features contain global topological information about the intensity landscape. We describe the mathematical properties of the Hamiltonian streamline-guided features as well as algorithms for extracting them. To test the new features, we use a face classification experiment and compare them against a standard local gradient feature: Haar-like features. Our experiments show that the global nature of the Hamiltonian streamline-guided features complements the local Haar-like features. For images of the same size, our feature space is demonstrably more compact and descriptive resulting in significantly fewer features needed for comparative classification accuracy and speed. When the two types of features are combined, superior performance is achieved.