Principal Component Analysis (PCA) is widely used in the field of medical image processing. In this paper, PCA is applied to align and fuse the images. When alignment, first, the centroids of the static and moving images are derived by computing the image moments and taken as the translation values for registration, then the subtraction of two rotation angles produced by using PCA to solve the covariance matrice of image coordinates is counted as the rotation values for registration, finally the moving image is aligned with the static one. The Closest Iterative Point (ICP) algorithm exists some problems which worth improving. Therefore, we combine PCA with ICP to align the images in this paper. The translation and rotation values derived by PCA are views as the initial request parameters of ICP, which is conducive to further advancing the registration accuracy. The experimental results show that the combination method has a fairly simple implementation, low computational load, good registration accuracy, and also can efficiently avoid trapping in the local optima. When fusion, a slipping window with size being is first moved across the fusing images to construct sub-block with size also being , then the eigenvectors of the covariance matrix created by using PCA to each sub-block are acquired, finally the absolute values of the eigenvectors are added to compute the fusion coefficient of the central pixel of each sub-block and the images are fused. The results reveal that this proposed fusion method is superior to the traditional PCA-based image fusion.

[1] Arun K., Huang T., and Blostein S., “Least- Squares Fitting of Two 3-D Point Sets,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 9, no. 5, pp. 698-700, 1987.

[2] Besl P. and Mckay N., “A Method for Registration of 3-D Shapes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, 1992.

[3] Can A., Stewart C., Roysam M., and Tanenbaum H., “A Feature-Based, Robust, Hierarchical Algorithm for Registration Palm of Images of the Curved Human Retina,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 347-364, 2002.

[4] Daneshvar S. and Ghassemian H., “MRI and PET Image Fusion by Combining IHS and Retina-Inspired Models,” Information Fusion, vol. 11, no. 2, pp. 114-123, 2010.

[5] Gulrez T. and Al-Odienat A., “A New Perspective On Principal Component Analysis Using Inverse Covariance,” The International Arab Journal of Information Technology, vol. 12, no. 1, pp. 104-109, 2015.

[6] Hu M., “Visual Pattern Recognition by Moment Invariants,” IRE Transactions on Information Theory, vol. 8, no. 2, pp. 179-187, 1962.

[7] Kaneko S., Kondo T., and Miyamoto A., “Robust Matching of 3D Contours Using Iterative Closest Point Algorithm Improved by M-Estimation,” Pattern Recognition, vol. 36, no. 9, pp. 2041-2047, 2003.

[8] Laliberte F., Gagnon L., and Sheng Y., “Registration and Fusion of Retinal Images-An Evaluation Study,” IEEE Transactions on Medical Imaging, vol. 22, no. 5, pp. 661-673, 2003.

[9] Li S., Yang B., and Hu J., “Performance Comparison of Different Multi-Resolution Transforms for Image Fusion,” Information Fusion, vol. 12, no. 2, pp. 74-84, 2011.

[10] Liu W. and Ribeiro E., “Incremental Variations of Image Moments for Nonlinear Image Registration,” Signal, Image and Video Processing, vol. 8, no. 3, pp. 423-432, 2014.

[11] Liu Y., Cheng H., Huang J., Zhang Y., Tang X., and Tian J., “An Effective Non-rigid Registration Approach for Ultrasound Image Based on „Demons‟ Algorithm,” Journal of Digital Imaging, vol. 26, no. 3, pp. 521-529, 2013.

[12] Maintz J. and Viergever M., “A Survey of Medical Image Registration,” Medical Image Analysis, vol. 2, no. 1, pp. 1-36, 1998.

[13] Miao Q., Shi C., Xu P., Yang M., and Shi Y., “A Novel Algorithm of Image Fusion Using Shearlets,” Optics Communications, vol. 284, no. 6, pp. 1540-1547, 2011.

[14] Naidu V. and Raol J., “Pixel-Level Image Fusion Using Wavelets and Principal Component Nalysis,” Defence Science Journal, vol. 58, no. 3, pp. 338-352, 2008.

[15] Nejati M. and Pourghassem H., “Multiresolution Image Registration in Digital X-Ray Angiography with Intensity Variation Modeling,” Journal of Medical Systems, vol. 38, no. 1, pp. 10-18, 2014.

[16] Pan M., Jiang J., Rong Q., Zhang F., Zhou H., and Nie F., “A Modified Medical Image Registration,” Multimedia Tools and Applications, vol. 70, no. 3, pp. 1585-1615, 2014. 520 The International Arab Journal of Information Technology, Vol. 14, No. 4, July 2017

[17] Park H., Bland P., Brock K., and Meyer C., “Adaptive Registration Using Local Information Measures,” Medical Image Analysis, vol. 8, no. 4, pp. 465-473, 2004.

[18] Wang Z., Ma Y., and Gub J., “Multi-Focus Image Fusion using PCNN,” Pattern Recognition, vol. 43, no. 6, pp. 2003-2016, 2010.

[19] Wong R., “Scene Matching with Invariant Moments,” Computer Graphics and Image Processing, vol. 8, no. 1, pp. 16-24, 1978.

[20] Yang L., Guo B., and Ni W., “Multimodality Medical Image Fusion Based on Multiscale Geometric Analysis of Contourlet Transform,” Neurocomputing, vol. 72, no. 3, pp. 203-211, 2008. Meisen Pan was born in 1972 and graduated from Hunan Normal University, China, in 1995. He received the M.S. degree from Huazhong University of Science and Technology, China, in 2005. He obtained the Ph.D. degree from Central South University, China, in 2011. He has published more than 30 papers on journals and conferences. His research interests include biomedical image processing, information fusion and software engineering. Jianjun Jiang was born in 1971 and graduated from Hunan University of Arts and Science, China, in 2010. She has published 2 papers on journals and conferences. Her research interests include image processing and information retrieves. Fen Zhang was born in 1972 and graduated from Hunan University, China, in 1996. He received the M.S. degree from Hunan University, China, in 2005. He has published more than 10 papers on journals and conferences. His research interests include image processing and computer graphics. Qiusheng Rong was born in 1973 and graduated from Central China Normal University, China, in 1996. He received the M.S. degree from Central China Normal University of Science and Technology, China, in 2001. He has published more than 10 papers on journals and conferences. His research interests include data mining and image processing.