Image recognition on the neural network based on multi-valued neurons

Abstract

Multi-valued neurons are the neural processing elements with complex-valued weights, huge functionality, quickly converged learning algorithms. Such features of the multi-valued neurons may be used for solution of the different kinds of problems. A neural network with multi-valued neurons for image recognition is considered in the paper. Such a network with original architecture analyzes the phases of the Fourier spectral coefficients corresponding to the low frequencies. The quickly converged learning algorithm and huge functionality of multi-valued neurons allow the neural network to achieve 100% successful recognition of different classes of images including the blurred and corrupted ones. Simulation results are presented on the example of face recognition.