Image registration based on Hough transform and phase correlation

被引：0

作者：

Li, ZK ^{[1
]}

Yang, XH ^{[1
]}

Wu, LN ^{[1
]}

机构：

[1] Southeast Univ, Dept Radio, Nanjing 210096, Peoples R China

来源：

PROCEEDINGS OF 2003 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS & SIGNAL PROCESSING, PROCEEDINGS, VOLS 1 AND 2 | 2003年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, Hough transform and phase correlation are combined to solve the problem of image registration. Based on 1D phase correlation, a method is proposed to obtain the angle of rotation by searching a angle ridge. After de-rotation, the traditional 2D phase correlation is imported to get the translation. The method can take full advantage of the high efficiency of FFT. Experiments show that the proposed method can detect the rotation and translation between images efficiently and exactly.

引用

页码：956 / 959

页数：4

共 9 条

[1]

AITOVA B, 2002, IMAGE REGISTRATION M

[2]

ALLINEY S, 1986, DIGITAL IMAGE REGIST, V8

[3]

CASTRO ED, 1987, IEEE PAMI, V9

[4]

HEEGER DJ, 1998, PSYCH, P267

[5]

Hill L, 1999, IEE CONF PUBL, P721, DOI 10.1049/cp:19990418

[6] Projection-based, frequency-domain estimation of superimposed translational motions [J].

Milanfar, P .

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1996, 13 (11) :2151-2162

[7]

Onishi H, 1996, INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, PROCEEDINGS - VOL III, P827, DOI 10.1109/ICIP.1996.560874

[8]

PAO DCV, 1992, IEEE PAMI, V14

[9]

XIE H, 2000, ICORG 2000 ICRS GIS, V1, P397

← 1 →