期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：3
页码：1046-1049
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Medical image fusion is the process of combining two or more images of the same scene, from the single or multiple imaging modalities, to obtain the image which preserves important features from each. Different medical imaging modalities used in fusion are Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), and Single-Photon Emission Computed Tomography (SPECT). Image fusion techniques are broadly classified into two categories; spatial domain image fusion (pixel level) and transform domain image fusion. The basic spatial domain image fusion methods are Simple Average, Select maximum, Select Minimum, Principal Component Analysis (PCA), Intensity-Hue-Saturation (IHS) transform, and Singular Value Decomposition (SVD) etc. Examples for transform domain image fusion methods are Pyramid Fusion Algorithms, Discrete Wavelet Transform (DWT), DT-CWT, Stationary Wavelet Transform (SWT), and Curvelet Transform etc. The image fusion can be performed at different levels such as pixel, feature, signal, and decision level. In this paper image fusion methods such as Simple Average, Select maximum, Select Minimum, Principal Component Analysis (PCA), and Discrete Wavelet Transform (DWT) are explained and are compared using the quality metrics Peak S ignal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE).
