Non-rigid Registration of Ultrasonic Image Based on Matching Corresponding Landmarks
With the rapid development of medical imaging technology, many different medical imaging types of equipment were developed. Different medical imaging equipments have different advantages and shortcomings, which make it urgent to integrate those images obt
- PDF / 132,607 Bytes
- 5 Pages / 439.37 x 666.142 pts Page_size
- 83 Downloads / 190 Views
Non-rigid Registration of Ultrasonic Image Based on Matching Corresponding Landmarks Xuan Wang
Abstract With the rapid development of medical imaging technology, many different medical imaging types of equipment were developed. Different medical imaging equipments have different advantages and shortcomings, which make it urgent to integrate those images obtained by different imaging equipment. In general, a mixed registration approach includes coarse registration, corner detector and refines registration three steps. In order to achieve the accuracy of the registration precise in the medical treatment, we proposed the new medical image registration algorithm based on a kind of automatic feature points. First, the SIFT algorithm and shape factor are used to produce landmarks. The primary data set which includes both the local and global feature vectors is constructed by using these landmarks. Finally, the registration is carried out on the data set by thin plate spline interpolation. The simulation results show that, the speed of the algorithm is improved significantly based on the high accuracy of the registration. Keywords Ultrasonic image • Image registration • Principle component analysis
40.1
Introduction
Image registration is the process of overlaying two or more images of the same scene taken at different times, from different viewpoints, and/or by different sensors. It geometrically aligns two images—the reference and sensed images. The present differences between images are introduced due to different imaging conditions [1]. Image registration is a crucial step in all image analysis tasks in
X. Wang (*) College of Health Science and Computer Nursing, Wuhan Polytechnic University, Wuhan, Hubei, China e-mail: [email protected] S. Zhong (ed.), Proceedings of the 2012 International Conference on Cybernetics 309 and Informatics, Lecture Notes in Electrical Engineering 163, DOI 10.1007/978-1-4614-3872-4_40, # Springer Science+Business Media New York 2014
310
X. Wang
which the final information is gained from the combination of various data sources like in image fusion, change detection, and multichannel image restoration. In the last decades, image acquisition equipment has experienced rapid development and expansion of the number and diversity research obtains the image, call to be automatic image registration. A comprehensive survey of image registration method is by Brown in 1992 published [2]. The paper was intended to introduce the method, in this way the map of the present situation of the development of the registration of technology [3]. According to the database of scientific information research institute (ISI), in the past decade, more than 1,000 papers published on the topic of image registration. Methods published before 1992, become a classic or introduction key ideas, it is still in use, including also keep continuity and give complete image registration research point of view [4]. In the paper, we proposed the new medical image registration algorithm based on a kind of automatic feature po
Data Loading...
