Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.635797
Title: Texture classification and segmentation using one dimensional discrete Fourier transforms
Author: Arof, H.
Awarding Body: University of Wales Swansea
Current Institution: Swansea University
Date of Award: 1997
Availability of Full Text:
Access through EThOS:
Abstract:
This thesis introduces a texture descriptor that is invariant to rotation. The new texture descriptor utilizes the property of the magnitudes of Fourier transform coefficients that do not change with spatial shift of input elements. Since rotating an image by an arbitrary angle does not change pixel intensities in an image but shifts them in circular motion, the notion of producing texture features invariant to rotation using 1-D Fourier transform coefficients can be realized if the relationship between circular motion and spatial shift can be established. By analyzing individual circular neighbourhoods centered at every pixel in an image, local and global texture attributes of the image can be described. Rotating the image has a similar effect as spatially shifting the pixels in the circular neighbourhood around without altering their intensities. A number of sequences can be formed by the intensities of pixels at various fixed distances from the center of the neighbourhood. Fourier transforming the sequences would generate coefficients that contain the texture information of the neighbourhood. From the magnitudes of these coefficients, several rotation invariant features are obtained. The capabilities of the new features are investigated in a number of classification and segmentation experiments. The experimental results compare favourably with those of prominent descriptors like the circular autoregressive model, the wavelet transform, the Gaussian Markov radom field and the co-occurrence matrix. In the majority of the instances, the new method shows superior performance.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.635797  DOI: Not available
Share: