Abstract
In this research building system to recognition texture images using artificial neural networks. The system consists of two phases: phase extraction important feature of each texture by using an algorithm Principal Components Analysis (PCA) and recognition phase which recognize these feature by using Elman network were trained network on a number of various texture models down to the steady-state network and then test the network by input samples of textures. The experiments show that the method achieves high performance and produces 92% recognition rate.