Fuzzy Numerical Morphological approach for Super Resolution of MR Brain Images

Magnetic resonance imaging (MRI) is an incredible medicinal technology provides relative information regarding the parts of the human body. For the diagnosis, high resolution MR images are essential to extract the detailed information about the diseases. But high resolution (HR) images will be constructed from number of low resolution (LR) images. It is time consuming process to construct a HR image from the number of LR images. However, with the measured single MR images it’s a challenging issue in extracting the detailed information associated to disease for the posterior analysis or treatment. In general, to improve the contrast of MR image histogram equalization has to be performed. In the proposal, for the resolution enhancement of the MR brain images a soft computing approach i.e. fuzzy mathematical approach is implemented. Irrespective of the region, it is possible to manipulate the intensities over the entire region with the help of fuzzy logic so that the resolution will be improved. To analyze the proposal qualitatively and quantitatively different performance image metrics are evaluated like PSNR, entropy etc. And from the results it can be observed that better results are obtained with the proposal when compared with the conventional methods.