Analysis And Applications Of Non-Subsampled Contourlet Transform

This book gives how to design an efficient MIF system which mainly concentrates on the edges,textures and boundaries of medical images.Further it also tries to achieve a fused image which could be shift-invariant,rotation-invariant, multi-scale and multidirectional in nature.The complete accomplishment of this approach is done in the Non-subsampled Contourlet Transform(NSCT) domain.Initially the source images are transformed through NSCT into Low frequency and high frequency sub band images.Since the NSCT is shift-invariant,multi-scale and multi-directional in nature,the source images are transformed through NSCT only such that the fused images should be robust to such issues. To make the fused image rotation-invariant,the dominant features in every orientation needs to be captured and this is accomplished through Gabor filter. Two new fusion rules are also derived based on the Angular Consistency(AC) and Spatio-Frequency energy of low frequency sub bands and high frequency sub bands respectively.The new rule based on AC helps in the observation of phase variations in the low frequency sub bands and the Spatio-Frequency energies noise invariant.

Autorentext
Devanna, H. Dr. H. Devanna has received Ph.D from Jawaharlal Nehru Technological University Anatapur, Anathapuramu, Andhra Pradesh, India, in medical image processing. He has twenty years of teaching experience. He published more than 35 Paper in international journals, 12 Papers in international conferences and 8 Papers in national conferences.