|
|||||
|
Hala S. Own
National Research Institute of Astronomy and Geophysics, Helwan, Cairo, Egypt
Abstract :
Shift invariance and directional selectivity are two important transform properties that crucially affected the performance of automatic image registration in the transform domain. Although the non redundant wavelet transform enjoys several desirable properties, it is shift variant and yield distinctions between only three features orientations, horizontal, vertical and diagonal. Using complex wavelet transform, guarantees improve the shift invariance and directional selectivity properties of the transform, thereby enhancing the performance of automatic image registration algorithm that operates in the wavelet transform domain. In this paper we present a robust image registration technique, which employs complex wavelet transform. The experiments show that the automatic image registration algorithm proposed here improves the computational efficiency and yields robust and consistent image registration compared with other types wavelet transform.
Keywords: Image Registration, Multiresolution Entropy, Mutual Information, complex wavelet transform, Control Point Extraction, Q-shift dual tree complex wavelet transform , and Astronomical data. Biography:
BibTex: @ARTICLE{P1150442002,
AUTHOR = {Hala S. Own},
TITLE = {An Efficient Image Registration Algorithm Based on Q-Shift Complex Wavelet Transform (Q-Shift CWT)}, JOURNAL = {ICGST International Journal on Graphics, Vision and Image Processing}, YEAR = {2005}, MONTH={Jan}, VOLUME = {05}, ISSUE={2}, PAGES={9--15} } (
|
|||||
|
|