THE COMPARISON OF ALGORITHMS OF RECOGNITION OF IMAGES HOPFILD’S NEURAL NETWORKS

oleh: Anna Illarionovna Pavlova, Ksenya Anatolevna Bobrikova

Format: Article
Diterbitkan: Science and Innovation Center Publishing House 2016-05-01

Deskripsi

The main advantage of artificial neural networks (ANN) in recognition of the cottages, is in their functioning like a human brain. The paper deals with image recognition neuron Hopfield’s networks, a comparative analysis of the recognition images by a projection’s method and the Hebb’s rule. For these purposes, was developed program with C# in Microsoft Visual Studio 2012. In this article to recognition for images with different levels of distortion were used. The analysis of results of recognition of images has shown that the method of projections allows to restore strongly distorted images (level of distortions up to 25–30 percent)