An improved medical image fusion algorithm based on wavelet transform

Medical image fusion has very important value of application for medical image analysis and diagnosis. In this paper, the traditional method of wavelet fusion is improved and a new algorithm of medical image fusion is presented. When choosing high frequency coefficients, the regional edge intensities of each sub-image are calculated to realize adaptive fusion. The low frequency coefficient choosing is based on edges of images, so that the fused image can preserve all useful information and appears clearly. We apply the traditional and improved fusion algorithms based on wavelet transform to fuse images and also evaluate the fusion results. Experimental results show that this algorithm can effectively retain detail information of original images and enhance their edge and texture features. This new algorithm is better than traditional fusion algorithm based on wavelet transform.

[1]  Liu Gui A WAVELET-DECOMPOSITION-BASED IMAGE FUSION SCHEME AND ITS PERFORMANCE EVALUATION , 2002 .

[2]  Konstantinos N. Plataniotis,et al.  Retrieval of images from artistic repositories using a decision fusion framework , 2004, IEEE Transactions on Image Processing.

[3]  Li Jie,et al.  Image fusion scheme based on local gradient , 2005, Proceedings. 2005 International Conference on Communications, Circuits and Systems, 2005..

[4]  G. Qu,et al.  Information measure for performance of image fusion , 2002 .

[5]  G. Piella New quality measures for image fusion , 2004 .

[6]  Bin Zhang,et al.  Study on image fusion based on different fusion rules of wavelet transform , 2010, 2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE).

[7]  Chen,et al.  Research and Realization of Medical Image Fusion Based on Three-Dimensional Reconstruction , 2007 .

[8]  C Y Wen,et al.  Multi-resolution image fusion technique and its application to forensic science. , 2004, Forensic science international.

[9]  Vincent Barra,et al.  A General Framework for the Fusion of Anatomical and Functional Medical Images , 2001, NeuroImage.

[10]  Cedric Nishan Canagarajah,et al.  Fusion of 2-D images using their multiscale edges , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.