Image Registration Using Rotation Normalized Feature Points

In this paper a registration method based on Harris corners is proposed. It is composed of three main steps: extraction of feature point using a Harris corner detector, obtaining the correspondence between the features points of the reference and input image based on rotation normalized gray level information around the corners, and estimating the transformation parameters mapping the input image to the reference one by applying RANSAC. Experimental results illustrate the proposed algorithm is robust to translation, rotation, and slight scaling.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  Yao Jianchao.  Image registration based on both feature and intensity matching , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[3]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[4]  B. N. Chatterji,et al.  An FFT-based technique for translation, rotation, and scale-invariant image registration , 1996, IEEE Trans. Image Process..

[5]  Richard Szeliski,et al.  Video mosaics for virtual environments , 1996, IEEE Computer Graphics and Applications.

[6]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[7]  George Wolberg,et al.  Robust image registration using log-polar transform , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[8]  Rachid Deriche,et al.  A Robust Technique for Matching two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry , 1995, Artif. Intell..

[9]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[10]  Conor Heneghan,et al.  Retinal image registration using control points , 2002, Proceedings IEEE International Symposium on Biomedical Imaging.