Multimodal Medical Image Fusion Through a New DWT Based Technique
Medical image fusion can help physicians to extract thefeatures that may not be normally visible in images by differentmodalities. In this paper, a novel discrete wavelet transform(DWT) based technique for medical image fusion is presented.Firstly, the medical images to be fused are decomposed by theDWT. Secondly, by considering the characteristics of humanvisual system (HVS) and the physical meaning of the waveletcoefficients, new different fusion schemes are performed on lowfrequency and high frequency bands separately followed by awindow-based consistency verification. Finally, the fused image isconstructed by the inverse DWT (IDWT) with all the combinedcoefficients. Experimental results on both simulated and realmedical images can indicate that the proposed method is effectiveand provides a significant improvement over severalconventional fusion methods.
Yong Yang
School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013, China
国际会议
成都
英文
1-4
2010-06-18（万方平台首次上网日期，不代表论文的发表时间）