In point-based monomodal image registration, registration accuracy relies heavily on control point (CP) locations and correspondences. However, CP extraction and correspondence establishment are still difficult under complex deformations, such as elastic deformations. To solve this problem, we present a novel approach to optimizing CP locations and simultaneously establishing the proper correspondence between these points. An expectation-maximization-like model and a refinement mechanism are proposed to achieve CP optimization as well as correspondence establishment. Experimental results for artificial and real registration tasks show that the proposed approach is robust and has good convergence behavior.
In image local elastic transformation, compact support radial basis functions are used to implement image elastic
deformation. The elastic deformation area is related to the support of the radial basis function. However, how to choose
the support based on space distribution of landmarks still is an unresolved problem. In this paper, the relation between
the support and three landmarks space locations is analyzed using simple triangle structure for Wendland radial basis
function. Moreover, for landmarks set, Delaunay triangle is constructed to obtain the support of each triangle, and the
optimal support of radial basis function is chosen as the maximum. Experiments of artificial images and medial images
show the feasibility of our conclusions.
Standard Mutual Information function contains local maxima, which make against to convergence of registration transformation parameters for automated multimodality image registration problems. We proposed Feature Potential Mutual Information (FPMI) to increases the smoothness of the registration measure function and use Particle Swarm Optimization to search the optimal registration transformation parameter in this paper. At first, Edges of images are detected. Next, edge feature potential is defined by expanding edges to the neighborhood region using potential function. Each edge point influences the whole potential field, just like the particle of physics in the gravitation field space. FPMI is computed on the edge feature potential of two images. It substitutes the edge feature potential values for gray values in images. It can avoid great change of joint probability distribution and has less local maxima. The registration accuracy of FPMI is analyzed under different edge detection cases. It is shown that the registration accuracy of FPMI is more accurate and more robust than that of MI. Maximization of FPMI is done by PSO. PSO combines local search methods with global search methods, attempting to balance exploration and exploitation. Its complex behavior follows from a few simple rules and has less computational complexity. Multimodal medical images are used to compare the response of FPMI and MI to translation and rotation. Experiments show that FPMI is smoother and has less local fluctuations than that of MI. Registration results show that PSO do it better than Powell’s method to search the optimal registration parameters.
A new technique is developed for the data fusion of multispectral image and panchromatic image. The intensity component of fusion image is modified by combine multispectral information and high-resolution information, which is determined by image edge intensity. The fusion image is reconstructed by means of the inverse IHS transform. Experiment comparison shows that our method performing better in preserving spatial resolutions and color content than that of traditional IHS transform technique and wavelet transform fusion method.
The weighting exponent m is an important parameter in fuzzy c-means (FCM) algorithm. In this paper, three basic problems about m in FCM algorithm: clustering validity method based on optimal m (or whether does optimal m exist), how does m effect on the performance of fuzzy clustering, and which is the proper range of m in general applications, are studied with the knee of objective function Jm, and fuzzy decision-making methods. Numerical experimental results show that the optimal m* for specific data set does exist. Moreover, a group of numerical experimental results indicate that, within the range of m (epsilon) (1.5, 3.5), the optimal m* monotone increase linearly against the separability (rho) of data set. So in practical applications, one can choose the value of m within the range of [1.5, 3.5].