Pattern Recognition and Increasing of the Computational Efficiency of a Parallel Realization of the Probabilistic Neural Network with Homogeneity Testing

摘要

The research subject is the computational complexity of the probabilistic neural network (PNN) in the pattern recognition problem for large model databases. We examined the following methods of increasing the efficiency of a neural-network classifier: a parallel multithread realization, reducing the PNN to a criterion with testing of homogeneity of feature histograms of input and reference images, approximate nearest-neighbor analyses (Best-Bin First, directed enumeration methods). The approach was tested in facial-recognition experiments with FERET dataset.