A compact harmonic code for early vision based on anisotropic frequency channels

• Published in: Computer vision and image understanding 2010-06, Vol.114 (6), p.681-699
• Main Authors: Sabatini, Silvio P., Gastaldi, Giulia, Solari, Fabio, Pauwels, Karl, Van Hulle, Marc M., Diaz, Javier, Ros, Eduardo, Pugeault, Nicolas, Krüger, Norbert
• Format: Article
• Language: English
• Subjects: Anisotropy; Applied sciences; Artificial intelligence; Bio-inspired vision processing; Channels; Computer science; control theory; systems; Early vision; Exact sciences and technology; Filtering; Harmonics; Image representations; Motion; Multichannel filtering; Pattern recognition. Digital image processing. Computational geometry; Phase-based image analysis; Representations; Stereo; Vision; Visual signals
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2010.03.008

The problem of representing the visual signal in the harmonic space guaranteeing a complete characterization of its 2D local structure is investigated. Specifically, the efficacy of anisotropic versus isotropic filtering is analyzed with respect to general phase-based metrics for early vision attributes. We verified that the spectral information content gathered through channeled oriented frequency bands is characterized by high compactness and flexibility, since a wide range of visual attributes emerge from different hierarchical combinations of the same channels. We observed that constructing a multichannel, multiorientation representation is preferable than using a more compact one based on an isotropic generalization of the analytic signal. Maintaining a channeled (i.e., distributed) representation of the harmonic content results in a more complete structural analysis of the visual signal, and allows us to enable a set of “constraints” that are often essential to disambiguate the perception of the different features. The complete harmonic content is then combined in the phase-orientation space at the final stage, only, to come up with the ultimate perceptual decisions, thus avoiding an “early condensation” of basic features. The resulting algorithmic solutions reach high performance in real-world situations at an affordable computational cost.