Medical Image Registration Algorithm Based on Sparse Random Projection and SIFT Transform

Abstract

Abstract:

SIFT (Scale-Invariant Feature Transform) has defects in computational complexity of its key point descriptor computing stage and in the high dimensionality of the key point feature vectors. To speed up the SIFT computation, a SIFT based on compressive sensing algorithm was proposed. By the sparse feature representation methods of compressive sensing theory, the feature vector of SIFT is extracted and the high-dimensional gradient derivative was decreased to low-dimensional sparse feature vector. Accordingly, Euclidean distance was introduced to compute the similarity and dissimilarity between feature vectors used for image registration and BBF（Best-Bin-First） data structure was used to avoid exhaustion. The experimental results show that the proposed algorithm has better performance than the standard SIFT algorithm while registering the affine transformation medical images. Comparing with the current modified SIFT algorithms, the real-time performance of the proposed algorithm is improved obviously.

Key words: image processing, image registration, scale-invariant feature transform, feature extraction, sparse random projection

CLC Number:

TP391.4

YANG Sa, ZHENG Zhi-shuo. Medical Image Registration Algorithm Based on Sparse Random Projection and SIFT Transform[J]. J4, 2015, 32(3): 283-289.

References

[1] Muders J, Hesser J. Stable and Robust Geometric Self-Calibration for Cone-Beam CT Using Mutual Information [J]. IEEE Transactions on Nuclear Science, 2014, 61(1): 202-217.
[2] XuHong-kui, JiangMing-yan,YangMing-qiang. Registration of Multimodal Brain Medical Images Based on Improved Optical Flow Model[J]. Acta Electronica Sinica, 2012,40(3):525-529. （许鸿奎, 江铭炎, 杨明强. 基于改进光流场模型的脑部多模医学图像配准[J]. 电子学报，2012, 40(3):525-529.）
[3]Lowe David G. Object recognition from local scale-invariant features[C]. Proceedings of the International Conference on Computer Vision 2, ICCV, 1999: 1150–1157.
[4] Lowe David G. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[5]Mahmoud H, Masulli F, Rovetta S. Feature-Based Medical Image Registration Using a Fuzzy Clustering Segmentation Approach[C]. Computational Intelligence Methods for Bioinformatics and Biostatistics. 9th International Meeting, CIBB 2012: 7845-7857.
[6]LiFang Wei, Lin Pan, Lin Lin, et al.. The Retinal Image Registration Based on Scale Invariant Feature[C]. 2010 3rd International Conference on Biomedical Engineering and Informatics, BMEI, 2010:639-643.
[7]Paganelli C, Peroni M, Riboldi M. Scale invariant feature transform in adaptive radiation therapy: a tool for deformable image registration assessment and re-planning indication[J]. Physics in Medicine and Biology, 2013, 58(02):287-299．
[8]Wang Jie-yu，Wang Jia-jun，Zhang Jing-ya.Non-rigid Medical Image Registration Based on Improved Optical Flow Method and Scale-invariant Feature Transform[J]. Journal of Electronics & Information Technology，2013, 35(5):1222-1228.（王婕妤，王加俊，张静亚. 基于改进光流场和尺度不变特征变换的非刚性医学图像配准[J]. 电子与信息学报，2013, 35(5):1222-1228.）
[9]Xu zhijing, Dai Huanlei, Cao Peipei. Processing of Sonar Image Based on Compressive Sensing[J]. Advanced Materials Research, 2011,301-303:719-723.
[10]Han Bing, Wu Feng, Wu Dapeng. Image representation by compressive sensing for visual sensor networks[J].
Journal of Visual Communication and Image Representation, 2010,21(4):325-333.
[11]Qiu Wei, Zhou Jianxiong, Zhao Hongzhong, et al.. Three-Dimensional Sparse Turntable Microwave Imaging Based on Compressive Sensing[J]. IEEE Geoscience and Remote Sensing Letters, 2014,12(2):826-830.
[12]Chen Yuheng, Zhou Jiankang, Chen Xinhua, et al.. Research on Principle and Experimentation of High-Resolution Optical Compressive Spectral Imaging[J]. Acta Optica Sinica, 2014，340111005.(陈宇恒，周建康，陈新华等. 高分辨光学压缩光谱成像方法与实验研究[J]. 光学学报，2014，34(1)：0111005-1—0111005-6.)
[13] Ling Xingxiu, Wei Zhihui, Xiao Liang et al.. Compressed sensing image reconstruction algorithm based on non-local regularization[J]. Systems Engineering and Electonics, 2013, 35(1):196-202.(李星秀，韦志辉，肖亮等.非局部正则化的压缩感知图像重建算法[J].系统工程与电子技术，2013, 35(1):196-202.)
[14]Yang Sa, Yang Chunling. Image Registration Algorithm Based on Sparse Random Projection and Scale-invariant Feature Transform[J]. Acta Optica Sinica, 2014, 341110001.(杨飒，杨春玲. 基于压缩感知与尺度不变特征变换的图像配准算法[J]. 光学学报，2014，34(11)：1110001-1—1110001-6.)
[15] Emmanuel Candès; Justin Romberg; Terence Tao. Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information[J]. IEEE Trans. on Information Theory, February 2006, 52(2):489-509.
[16] Fang Hong, Zhang Quanbing, Wei Sui. Method of image reconstruction based on very sparse random projection[J]. Computer Engineering and Applications, 2007, 43(22)：25-27．(方红，章权兵，韦穗．基于非常稀疏随机投影的图像重建方法[J]．计算机工程与应用，2007，43(22)：25-27．)
[17] Evans A C. BrainWeb: Simulated Brain Database[DB/OL].[2014-12-112].http://www.bic.mni.mcgill. ca/brainweb.