With the rapid development of medical imaging technology, medical image research and application has become a research hotspot. This paper offers a solution to non-rigid registration of medical images based on ordinal feature (OF) and manifold learning. The structural features of medical images are extracted by combining ordinal features with local linear embedding (LLE) to improve the precision and speed of the registration algorithm. A physical model based on manifold learning and optimization search is constructed according to the complicated characteristics of non-rigid registration. The experimental results demonstrate the robustness and applicability of the proposed registration scheme.
As a product combining inverse synthetic aperture technology with coherent laser technology, Inverse Synthetic Aperture
Imaging Ladar (ISAIL) overcomes the diffraction limit of the telescope’s aperture, while it supplies a much better range
resolution which will not get worse at long range when the diameter telescope optics becomes smaller. Compared with
traditional microwave imaging radar, SAIL can provide a much higher-resolution image because of shorter wavelength,
and its shorter imaging time for coherent integration takes a great part in practical application. The rotational motion of
target generates Migration through Range Cells (MTRC) because of the ultra-high resolution of ISAIL. Quadratic Phase
Error (QPE) caused by Migration through Range Cells (MTRC) during the imaging time makes ISAIL image smeared. It
is difficult to estimate the QPE through traditional motion compensation algorithm. To solve this problem in the case of
uniform rotation rate, a novel QPE compensation method, based on Phase Cancellation (PC), is proposed. Firstly, a
rough range of QPE coefficient related to the wave-length, length of the target, and the rotating angle is estimated. Then,
through 1-D search, the QPE coefficient is obtained exactly. Finally, the QPE compensation is achieved. The ISAIL
imaging experiments with numerical data validate the feasibility and effectiveness of the proposed algorithm.
Registration of medical images is an essential research topic in medical image processing and applications, and
especially a preliminary and key step for multimodality image fusion. This paper offers a solution to medical image
registration based on normalized multi-dimensional mutual information. Firstly, affine transformation with translational
and rotational parameters is applied to the floating image. Then ordinal features are extracted by ordinal filters with
different orientations to represent spatial information in medical images. Integrating ordinal features with pixel
intensities, the normalized multi-dimensional mutual information is defined as similarity criterion to register
multimodality images. Finally the immune algorithm is used to search registration parameters. The experimental results
demonstrate the effectiveness of the proposed registration scheme.
In order to provide comprehensive information and improve the accuracy of clinical diagnoses and surgical therapies,
medical image fusion is becoming a new hot topic. As the basic and key issue medical image registration has very
important meaning. This paper offers a solution to medical image registration based on maximization of mutual
information (MI) and particle swarm optimization (PSO). First, the rigid transformation with translational and rotational
parameters is applied to the floating image. As an increasingly popular matching criterion for image registration, MI is
adopted in this method. Theoretically, the maximization of MI is obtained if the transformed image and the reference
image are geometrically aligned. Then an improved PSO algorithm is used to search the registration parameters. The
experimental results demonstrate the effectiveness of the proposed registration scheme.
Anchorperson shot detection is of significance for video shot semantic parsing and indexing clues extraction in content-based news video indexing and retrieval system. This paper presents a model-free anchorperson shot detection scheme based on the graph-theoretical clustering and fuzzy interference. First, a news video is segmented into video shots with any an effective video syntactic parsing algorithm. For each shot, one frame is extracted from the frame sequence as a representative key frame. Then the graph-theoretical clustering algorithm is performed on the key frames to identify the anchorperson frames. The anchorperson frames are further refined based on face detection and fuzzy interference with if-then rules. The proposed scheme achieves a precision of 98.40% and a recall of over 97.69% in the anchorperson shot detection experiment.