papers AI Learner
The Github is limit! Click to go to the new site.

Provably scale-covariant networks from oriented quasi quadrature measures in cascade

2019-03-01
Tony Lindeberg

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.00289

PDF

http://arxiv.org/pdf/1903.00289


Similar Posts

Comments