A Novel Image Registration and Denosing Method for Multiple Sequence for MRI and CT Image

Hatim Zoebdini, Deepti Agrawal
2016 unpublished
The Medical Images normally have a problem of high level components of noises. There are different techniques for producing medical images such as Magnetic Resonance Imaging (MRI), X-ray, Computed Tomography and Ultrasound, during this process noise is added that decreases the image quality and image analysis. Image denosing is an important task in image processing, use of spectral subtraction improves the quality of an image and reduces noise level. Noise reduction is an important step for any
more » ... ortant step for any complicated algorithms, in computer vision and image processing. In this paper proposed a hybrid method for medical image denosing for improvement of CT and MRI image for brain stroke and brain tumor. The process of CT and MRI image gets the high component value of noise in environment. For the reduction of these noise used wavelet transform domain method. The wavelet transform method is well recognized method for noise reduction. In wavelet transform method the local noise component value are not considered. Then after the denosing process noise are still remain in CT and MRI image. For these low components value collection used multiple sequences. And finally used self-organized map network.