Automatic image annotation is a promising solution to enable semantic image retrieval via keywords. In this paper, we propose a multi-level approach to annotate the semantics of n...
In this paper, we propose novel blur invariant features for the recognition of objects in images. The features are computed either using the phase-only spectrum or bispectrum of th...
We describe an algorithmfor reconstructing a scene containing multiple moving objects. Given a monocular image sequence, we recover the scene structure, the trajectories of the mo...
Two hybrid systems for classifying seven categories of human facial expression are proposed. The £rst system combines independent component analysis (ICA) and support vector mach...
Ioan Buciu, Constantine Kotropoulos, Ioannis Pitas
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...