Efficient image registration using fast principal component analysis

TY - GEN

T1 - Efficient image registration using fast principal component analysis

AU - Reel, Parminder Singh

AU - Dooley, Laurence S.

AU - Wong, Patrick

PY - 2013/2/21

Y1 - 2013/2/21

N2 - Incorporating spatial features with mutual information (MI) has demonstrated superior image registration performance compared with traditional MI-based methods, particularly in the presence of noise and intensity non-uniformities (INU). This paper presents a new efficient MI-based similarity measure which applies Expectation Maximisation for Principal Component Analysis (EMPCA-MI), to afford significantly lower computational complexity, while providing analogous image registration performance with other feature-based MI solutions. Experimental analysis corroborates both the improved robustness and faster runtimes of EMPCA-MI, for different test datasets containing both INU and noise artefacts.

AB - Incorporating spatial features with mutual information (MI) has demonstrated superior image registration performance compared with traditional MI-based methods, particularly in the presence of noise and intensity non-uniformities (INU). This paper presents a new efficient MI-based similarity measure which applies Expectation Maximisation for Principal Component Analysis (EMPCA-MI), to afford significantly lower computational complexity, while providing analogous image registration performance with other feature-based MI solutions. Experimental analysis corroborates both the improved robustness and faster runtimes of EMPCA-MI, for different test datasets containing both INU and noise artefacts.

U2 - 10.1109/ICIP.2012.6467196

DO - 10.1109/ICIP.2012.6467196

M3 - Conference contribution

SN - 9781467325349

SP - 1661

EP - 1664

BT - 19th IEEE International Conference on Image Processing

PB - IEEE

T2 - 19th IEEE International Conference on Image Processing (ICIP 2012)

Y2 - 30 September 2012 through 3 October 2012

ER -