期刊论文

Wei, Yantao

英文

Pattern Recognition

0031-3203

2014

47

4

1674-1688

10.1016/j.patcog.2013.10.008

This work was supported in part by the National Natural Science Foundation of China under Grants nos. 61075116 , 91330118, 61273244, 11371007 and 11071058 , the Natural Science Foundation of Hubei Province under Grants nos. 2009CDB387 and 2010CDA008 , Multi-Year Research of University of Macau under Grants nos. MYRG205(Y1-L4)-FST11-TYY and MYRG187(Y1-L3))-FST11-TYY , Start-up Research of University of Macau under Grant no. SRG010-FST11-TYY , Science and Technology Development Fund (FDCT) of Macau FDCT-100-2012-A3 and Scientific Research Starting Foundation of Central China Normal University .

本校为通讯机构

Image similarity measure has been widely used in pattern recognition and computer vision. We usually face challenges in terms of rotation and scale changes. In order to overcome these problems, an effective similarity measure which is invariant to rotation and scale is proposed in this paper. Firstly, the proposed method applies the log-polar transform to eliminate the rotation and scale effect and produces a row and column translated log-polar image. Then the obtained log-polar image is passed to hierarchical kernels to eliminate the row and c...