Intelligent Edge Detection using a CUDA Simulator of Multilayer Neural Network Based on Multi-Valued Neurons

In this paper, we consider the edge detection problem using an intelligent approach. We use a multilayer neural network based on multi-valued neurons (MLMVN) as an intelligent edge enhancer. MLMVN is a complex-valued neural network and it has many advantages over classical neural networks. It significantly outperforms a classical multilayer feedforward neural network in terms of learning speed, number of parameters employed, and generalization capability. MLMVN has already shown its efficiency in solving edge detection problem. Here we significantly improve its performance employing a GPU software simulator of MLMVN, which allows parallelization of the learning process. This makes it possible to speed up the learning process significantly. Compared to a regular CPU (serial) software simulator, a parallel simulator, which is described in this paper, is about 10 times faster for a 3-layer network with 9 inputs, 45 hidden neurons, and 1 output neuron.