Title :
Edge Detection and Anisotropic Diffusion for Tensor-Valued Images
Author :
Zhang, Fang ; Hancock, Edwin R.
Author_Institution :
Dept. of Comput. Sci., York Univ., UK
Abstract :
This paper considers feature space of DT-MRI as a differential manifold with an affine-invariant metric, where we generalise Di Zenzo´s structure tensor to tensor-valued images for edge detection. To improve the quality of the edges, we smooth out the noise by generalised Perona-Malik method for tensor images. We demonstrate our algorithm on both synthetic and real DT-MRI data.
Keywords :
edge detection; magnetic anisotropy; magnetic resonance imaging; smoothing methods; tensors; DT-MRI; Di Zenzo structure; Perona-Malik method; affine-invariant metric; anisotropic diffusion; diffusion tensor; edge detection; magnetic resonance imaging; noise smoothing; Anisotropic magnetoresistance; Computer science; Diffusion tensor imaging; Extraterrestrial measurements; Image edge detection; Image segmentation; Magnetic noise; Symmetric matrices; Tensile stress; Transmission line matrix methods; Image edge analysis; image restoration; object detection; smoothing methods;
Conference_Titel :
Image Processing, 2006 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
1-4244-0480-0
DOI :
10.1109/ICIP.2006.312467
