Provably scale-covariant networks from oriented quasi quadrature measures in cascade
This work addresses the challenge of building scale-covariant networks for texture analysis, representing an incremental advancement in biologically inspired computational models.
The authors tackled the problem of achieving scale and rotation covariance in hierarchical networks by developing a continuous model based on oriented quasi quadrature measures and cascade expansions, resulting in provable covariance properties and promising experimental results on three texture datasets.
This article presents a continuous model for hierarchical networks based on a combination of mathematically derived models of receptive fields and biologically inspired computations. Based on a functional model of complex cells in terms of an oriented quasi quadrature combination of first- and second-order directional Gaussian derivatives, we couple such primitive computations in cascade over combinatorial expansions over image orientations. Scale-space properties of the computational primitives are analysed and it is shown that the resulting representation allows for provable scale and rotation covariance. A prototype application to texture analysis is developed and it is demonstrated that a simplified mean-reduced representation of the resulting QuasiQuadNet leads to promising experimental results on three texture datasets.