Linear Prediction Spatial Filter for Discrimination of Similar Textures
Masaru Tsudagawa · IEEJ Transactions on Fundamentals and Materials · 2009
In this paper a spatial filter to discriminate similar textures is proposed. This spatial filter is composed by based on the linear prediction method. We have done two kinds of experiments to show the effectiveness of this proposed method. One is to the textures generated form the 2-dimentional random noise, and the other is to the texture recomposed from the Brodatz's texture. In the results it is showed that the proposed method is useful for both of the isotropic and an-isotropic textures.