Character Rotation Absorption Using a Dynamic Neural Network Topology: Comparison With Invariant Features
Abstract
This paper treats on rotation absorption in neural networks for multi-oriented character recognition. Classical approaches are based on several rotation invariant features. Here, we propose to use a dynamic neural network topology to absorb the rotation phenomenon. The basic idea is to preserve as most as possible the graphical information, that contains all the information. The proposal is to dynamically modify the neural network architecture, in order to take into account the rotation variation of the analysed pattern.We use too a specific topology that carry out a polar transformation inside the network. The interest of such a transformation is to transform the rotation problem from a problem to a problem, that is easier to treat. These proposals are applied on a synthetic and on a real EDF1 base of multi-oriented characters. A comparison is made with Fourier and Fourier-Mellin invariants.