This article studies the principle of the maximum mutual information method in gray-scale multi-modal medical image
registration. On the basis of mutual information, the goal function of registration is improved. This paper integrates
mutual information with edge correlation deviation and defines a new registration measure function. Image registration is
finished through optimizing this function. This method not only makes use of gray-scale mutual information of original
images but also contains the pixel relationship of edge images in two-dimensional level. It plays roll of compensation for
drawback of mutual information. Experiments prove that this is an effective image registration method.
Gradient amplitude and phase can't be used together in traditional edge detection procedure, So an algorithm for image
segmentation based on edge gradient estimate is given in this paper. First, a standard template is ascertained by the
gradient phase of the center pixel; then, estimate edge gradient is the absolute value of the correlation coefficient
between the normalized data vector and the template. The method of non-maximum suppression is used when
determining pixel local maximum point; hysteresis threshold is used when determining edge point. In both the treatment
process, the normalized gradient amplitude and phase would regard as distinguish basis, so this will increase the
capability of weak edge detection, and it can suppress the noise impact. This paper gives the relevant experiment result.