Author : Richa Gautam and Shilpa Datar

Image fusion finds numerous applications in remote sensing, satellite imaging, medical imaging etc. In medical science, in order to diagnose a disease, it is required that the image obtained from a particular modality should be highly informative and should have high accuracy and also it should have high spatial as well as high spectral resolution. However, most of the available modalities alone are not capable of doing it convincingly. To solve this problem, a technique called image fusion has been evolved, in which two or more images are fused together to make a new image. In medical image fusion two or more images obtained from different modalities are fused together to give us a desired image. Selection of fusion rule should be such that it must provide us all the relevant information and at the same time does not introduce any undesired features to the resulting image. In this paper we have proposed a method for fusing CT (Computed Tomography) and MRI (Medical Resonance Imaging) images based on second generation curvelet transform. Proposed method is compared with the results obtained after applying the other methods based on Discrete Wavelet Transform (DWT), Principal Component Analysis (PCA), and Discrete Cosine Transform (DCT). Entropy, Standard Deviation, Peak Signal to Noise Ratio (PSNR), Percentage Fit Error (PFE) and Spatial Frequency (SF) are used as performance metric evaluators.

Keywords: Image fusion, CT, MRI, Second Generation Curvelet Transform, DWT, PCA, Entropy, SD, PSNR, PFE, SF

Article published in International Journal of Current Engineering and Technology, Vol.7, No.1 (Feb-2017)