Home // International Journal On Advances in Intelligent Systems, volume 10, numbers 3 and 4, 2017 // View article

Recognition of Similar Marble Textures through Different Neural Networks with De-correlated Input Data

Authors:
Irina Topalova
Magdalina Uzunova

Keywords: MLP neural network; SOM neural network; texture recognition; pre-processing; de-correlation

Abstract:
The automated recognition of marble slab surface textures is an important task in the contemporary marble tiles production. The simplicity of the applied methods corresponds with fast processing, which is important for real-time applications. In this research a supervised learning of a multilayered neural network is proposed and tested. Aiming at high recognition accuracy, combined with simple pre-processing,the neural network is trained with different alternating input training sets including combination of high correlated and decorrelated input data. The de-correlated input data are also used for training of a self-organized map neural network,aiming to prove the efficiency of the pre-processing method also for unsupervised neural networks. The obtained good results in the recognition stage are represented, compared and discussed. Further research is proposed.

Pages: 474 to 479

Copyright: Copyright (c) to authors, 2017. Used with permission.

Publication date: December 31, 2017

Published in: journal

ISSN: 1942-2679