Direct Estimation of Non-Rigid Registrations
نویسندگان
چکیده
Registering images of a deforming surface is a well-studied problem. Solutions include computing optic flow or estimating a parameterized motion model. In the case of optic flow it is necessary to include some regularization. We propose an approach based on representing the induced transformation between images using Radial Basis Functions (RBF). The approach can be viewed as a direct, i.e. intensity-based, method, or equivalently, as a way of using RBFs as non-linear regularizers on the optic flow field. The approach is demonstrated on several image sequences of deforming surfaces. It is shown that the computed registrations are sufficiently accurate to allow convincing augmentations of the images.
منابع مشابه
Non-rigid motion estimation from hierarchical adaptive local affine registrations
Non-rigid image registrations have been widely employed in medical imaging to estimate the complex tissue deformations such as those caused by respiratory motion. To reduce the computational burden of non-rigid registration techniques, alternative approaches have been proposed which decompose the non-rigid registration problem into a combination of multiple more simple registration problems, su...
متن کاملDetection and correction of inconsistency-based errors in non-rigid registration
In this paper we present a novel post-processing technique to detect and correct inconsistency-based errors in non-rigid registration. While deformable registration is ubiquitous in medical image computing, assessing its quality has yet been an open problem. We propose a method that predicts local registration errors of existing pairwise registrations between a set of images, while simultaneous...
متن کاملA curvelet-based patient-specific prior for accurate multi-modal brain image rigid registration
We present a new non-uniform sampling method for the accurate estimation of mutual information in multi-modal brain image rigid registration. Most existing density estimators used for mutual information computation incorrectly assume that the intensity of each voxel is independent from its neighborhood. Our method uses the 3D Fast Discrete Curvelet Transform to reduce the sampled voxels' interd...
متن کاملUse of the CT component of PET-CT to improve PET-MR registration: demonstration in soft-tissue sarcoma.
We have investigated improvements to PET-MR image registration offered by PET-CT scanning. Ten subjects with suspected soft-tissue sarcomas were scanned with an in-line PET-CT and a clinical MR scanner. PET to CT, CT to MR and PET to MR image registrations were performed using a rigid-body external marker technique and rigid and non-rigid voxel-similarity algorithms. PET-MR registration was als...
متن کاملCombining patch-based strategies and non-rigid registration-based label fusion methods
The objective of this study is to develop a patch-based labeling method that cooperates with a label fusion using non-rigid registrations. We present a novel patch-based label fusion method, whose selected patches and their weights are calculated from a combination of similarity measures between patches using intensity-based distances and labeling-based distances, where a previous labeling of t...
متن کامل