Learning how to extract rotation-invariant and scale-invariant features from texture images
No Thumbnail Available
Learning how to extract texture features from noncontrolled environments characterized by distorted images is a still-open task. By using a new rotation-invariant and scale-invariant image descriptor based on steerable pyramid decomposition, and a novel multiclass recognition method based on optimum-path forest, a new texture recognition system is proposed. By combining the discriminating power of our image descriptor and classifier, our system uses small-size feature vectors to characterize texture images without compromising overall classification rates. State-of-the-art recognition results are further presented on the Brodatz data set. High classification rates demonstrate the superiority of the proposed system.
Classification (of information) , Computer networks , Image enhancement , Rotation , Textures , Brodatz , Classification rates , Data sets , Discriminating power , Distorted images , Feature vector (FV) , image descriptor , Invariant features , multiclass recognition , rotation invariant , Steerable pyramid (SP) , Texture features , texture images , Texture recognition , Feature extraction