Rotation-Invariant Texture Analysis and Classification by Artificial Neural Networks and Wavelet Transform

Authors: ABDULSAMET HAŞİLOĞLU

Abstract: A large number of approaches for texture analysis have been suggested for the purpose of texture classification. Recently, wavelet frames were proposed for texture features extraction. In this study, non-subsampled wavelet frame transform was used for feature extraction of 16 textures from a set of Brodatz' album by means of various wavelet families. Texture classification was accomplished by artificial neural network with a fast adaptive backpropagation algorithm. A new pyramidal-windowing algorithm is proposed, which forms randomly rotated texture windows of variable sizes texture windows for training a neural networks classifier, and perfect classification results were obtained.

Keywords: Texture, Wavelet transform, Artificial neural networks, Classification

Full Text: PDF