Hierarchical neural network for multiresolution image analysis

We propose an architecture for multiresolution classification based on a wavelet decomposition and a hierarchical neural network. Each layer of the neural network is a “frequency expert” associated with a single frequency channel. Higher layers in the hierarchy integrate the information provided by the layers below, leading to a network where different “experts” cooperate to explain the input data. We illustrate the performance of this architecture on edge detection, a problem which is well known to be best addressed in a multiresolution framework