MRI Brain Image Registration Using Hybrid Model

Image Registration is an important and challenging factor in the Medical Image Processing. This paper describes a new hybrid model for Image Registration through Magnetic Resonance Image (MRI). This model consists of three phases. In the first phase, film artifacts and unwanted portions of MRI Brain image are removed. Secondly, the noise and high frequency components are removed using weighted median filter (WM). Finally, Hybrid model is applied for registration phase in which this phase comprises of two methods namely non-rigid and rigid. In non-rigid, block based technique is implemented in which the   reference image and normal images are split in to number of blocks of size 64×64.Each and every corresponding blocks from reference image and normal images are compared using Ant colony optimization(ACO). if the images are similar, the resultant image obtained is given to rigid method as input. In rigid method, similarity measures are calculated for the given image which includes 1. Contrast checking (CC) 2. Sum of Square Difference (SSD) 3.Calculation of White cells and 4.point mapping.