This Article 
 Bibliographic References 
 Add to: 
Digital Analysis of Rotated Images
May 1993 (vol. 15 no. 5)
pp. 499-504

The problem of estimating the relative rotations of two images taken from the same scene is considered, and a numerical method for computing such rotations is presented. The main features of the proposed method consist of the possibility of fast in-place computations with no preliminary interpolation of the data and a considerable precision for moderate rotation angles. The final estimate is performed with a least square criterion, but in the present case, even such computations can be substantially simplified. A detailed analysis shows that for practical applications, the influence of discretization errors does not affect, in a relevant way, the precision of the results; that is also confirmed by numerical experiments.

[1] T. S. Huang (Ed.),Image Sequence Analysis. Berlin--New York: Springer 1981.
[2] P. E. Anuta, "Spatial registration of multispectral and multitemporal digital images using FFT techniques,"IEEE Trans. Geosci. Electron., vol. GE-8, pp. 353-368, 1980.
[3] Y. Bresler and S. J. Merhav, "Recursive image registration with application to motion estimation,"IEEE Trans. Acoust. Speech Signal Processing, vol. ASSP-35, pp. 70-85, 1987.
[4] E. Peli, R. A. Augliere, and G. T. Timberlake, "Feature-based registration of retinal images,"IEEE Trans. Med. Imaging, vol. MI-6, pp. 272-278, 1987.
[5] J. Biemond, L. Loijenga, D. E. Boekee, and R. H. J. M. Plompen, "A pel-recursive Wiener-based displacement estimation algorithm,"Signal Processing, vol. 13, pp. 399-412, 1987.
[6] C. D. Kuglin and D. C. Hines, "The phase-correlation image alignement method," inProc. IEEE 1975 Int. Conf. Cybern. Soc., 1975, pp. 163-165.
[7] S. Alliney and C. Morandi, "Digital image registration using projections,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, pp. 222-233, 1986.
[8] J. Weng, T.S. Huang, and N. Ahuja, "3-D motion estimation, understanding, and prediction from noisy image sequences,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, no. 3, 1987.
[9] A. Goshtasby, "Template-matching in rotated images,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-7, pp. 338-344, 1985.
[10] E. De Castro and C. Morandi, "Registration of translated and rotated images using finite Fourier transforms,"IEEE Trans. Pattern Anal. Machine Intell., vol. 9, no. 5, pp. 700-703, 1987.
[11] S. Alliney, "Linear operators and discrete transforms," inSignal Processing II: Theories and Applications(H. W. Schuessler, Ed.). Amsterdam: North-Holland, 1983, pp. 9-12.
[12] J. Wilkinson,Rounding Errors in Algebraic Processes. Englewood Cliffs, NJ: Prentice-Hall, 1963.
[13] I. S. Gradshteyn and I. M. Ryzhik,Tables of Integrals, Series and Products. New York: Academic, 1980.
[14] G. H. Golub and C. F. Van Loan,Matrix Computations. Baltimore, MD: Johns Hopkins University Press, 1989.
[15] A. Papoulis,Systems and Transforms with Application in Optics. New York: McGraw-Hill, 1968.

Index Terms:
relative rotation estimation; image processing; motion estimation; rotated images; numerical method; least square criterion; image processing; least squares approximations; motion estimation
S. Alliney, "Digital Analysis of Rotated Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 5, pp. 499-504, May 1993, doi:10.1109/34.211470
Usage of this product signifies your acceptance of the Terms of Use.