Color image registration based on quaternion Fourier transformation

The traditional Fourier Mellin transform is applied to quaternion algebra in order to investigate quaternion Fourier transformation properties useful for color image registration in frequency domain. Combining with the quaternion phase correlation, we propose a method for color image registration based on the quaternion Fourier transform. The registration method, which processes color image in a holistic manner, is convenient to realign color images differing in translation, rotation, and scaling. Experimental results on different types of color images indicate that the proposed method not only obtains high accuracy in similarity transform in the image plane but also is computationally efficient.

[1]  Stephen J. Sangwine,et al.  Hypercomplex Fourier Transforms of Color Images , 2007, IEEE Trans. Image Process..

[2]  Mutsuo Sano,et al.  A parametric template method and its application to robust matching , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  Baba C. Vemuri,et al.  A Quaternion Framework for Color Image Smoothing and Segmentation , 2011, International Journal of Computer Vision.

[4]  Liming Zhang,et al.  A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression , 2010, IEEE Transactions on Image Processing.

[5]  C. Eddie Moxey,et al.  Color-grayscale image registration using hypercomplex phase correlation , 2002, Proceedings. International Conference on Image Processing.

[6]  S. Sangwine,et al.  Vector phase correlation , 2001 .

[7]  Xiaokang Yang,et al.  2D Quaternion Fourier Transform: The Spectrum Properties and its Application in Color Image Registration , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[8]  Ming Zhu,et al.  Quaternion Fourier-Mellin moments for color images , 2011, Pattern Recognit..

[9]  Y. Hel-Or,et al.  A common framework for steerability, motion estimation, and invariant feature detection , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[10]  C. Eddie Moxey,et al.  Hypercomplex correlation techniques for vector images , 2003, IEEE Trans. Signal Process..

[11]  Shumin Fei,et al.  Color image registration via quaternion Fourier transform and parametric template method , 2010, 2010 8th World Congress on Intelligent Control and Automation.

[12]  Jianqi Zhang,et al.  Discrete-quaternion-Fourier-transform-based registration method for color images , 2010, 2010 International Conference on Audio, Language and Image Processing.

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

[14]  Henning Rasmussen,et al.  Local quaternion Fourier transform and color image texture analysis , 2010, Signal Process..

[15]  Eckhard Hitzer,et al.  Quaternion Fourier Transform on Quaternion Fields and Generalizations , 2007, ArXiv.

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

[17]  S. Sangwine.  Fourier transforms of colour images using quaternion or hypercomplex, numbers , 1996 .