A FAST CLASSIFICATION METHOD FOR SINGLE-PARTICLE PROJECTIONS WITH A TRANSLATION AND ROTATION INVARIANT

CSpace

	A FAST CLASSIFICATION METHOD FOR SINGLE-PARTICLE PROJECTIONS WITH A TRANSLATION AND ROTATION INVARIANT
	Wang Xia; Xu Guoliang
	2013
发表期刊	Journal of Computational Mathematics
ISSN	0254-9409
卷号	31 期号:2 页码:137
摘要	The aim of the electron microscopy image classification is to categorize the projection images into different classes according to their similarities. Distinguishing images usually requires that these images are aligned first. However, alignment of images is a difficult task for a highly noisy data set. In this paper, we propose a translation and rotation invariant based on the Fourier transform for avoiding alignment. A novel classification method is therefore established. To accelerate the classification speed, secondary-classes are introduced in the classification process. The test results also show that our method is very efficient and effective. Classification results using our invariant are also compared with the results using other existing invariants, showing that our invariant leads to much better results.
语种	英语
资助项目	[NSFC] ; [NSFC key project] ; [Funds for Creative Research Groups of China]
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/47512
专题	中国科学院数学与系统科学研究院
作者单位	中国科学院数学与系统科学研究院
推荐引用方式 GB/T 7714	Wang Xia,Xu Guoliang. A FAST CLASSIFICATION METHOD FOR SINGLE-PARTICLE PROJECTIONS WITH A TRANSLATION AND ROTATION INVARIANT[J]. Journal of Computational Mathematics,2013,31(2):137.
APA	Wang Xia,&Xu Guoliang.(2013).A FAST CLASSIFICATION METHOD FOR SINGLE-PARTICLE PROJECTIONS WITH A TRANSLATION AND ROTATION INVARIANT.Journal of Computational Mathematics,31(2),137.
MLA	Wang Xia,et al."A FAST CLASSIFICATION METHOD FOR SINGLE-PARTICLE PROJECTIONS WITH A TRANSLATION AND ROTATION INVARIANT".Journal of Computational Mathematics 31.2(2013):137.