Abstract
A theoretical framework is presented in which windowed Fourier phase (WFP) is introduced as the primary matching primitive. Zero-crossings and peaks correspond to special values of the phase. The WFP is quasi-linear and dense; and its spatial period and slope are controlled by the scale. This framework has the following important characteristics: 1) matching primitives are available almost everywhere to convey dense disparity information in every channel, either coarse or fine; 2) the false-target problem is significantly mitigated; 3) the matching is easier, uniform, and can be performed by a network suitable for parallel computer architecture; 4) the matching is fast since very few iterations are needed. In fact, the WFP is so informative that the original signal can be uniquely determined up to a multiplicative constant by the WFP in any channel. The use of phase as matching primitive is also supported by some existing psychophysical and neurophysiological studies. An implementation of the proposed theory has shown good results from synthesized and natural images.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
N. Ayache and B. Faverjon, Efficient registration of stereo images by matching graph descriptions of edge segments,Intern. J. Comput. Vis. 1(2):107–131, 1987.
H.H. Baker and T.O. Binford, Depth from edges and intensity based stereo,Proc. 7th Intern. Joint Conf. Artif. Intell., Vancouver, pp. 631–636, August 1981.
R.N. Bracewell,The Fourier transformation and its applications, 2nd ed.) McGraw-Hill: New York, 1986.
O.J. Braddick, A short-range process in apparent motion,Vision Research 14:519–527, 1974.
O.J. Braddick, Low-level and high-level processes in apparent motion,Phil. Trans. Roy. Soc. London, B, 290:137–151, 1980.
P.J. Burt, J.R. Bergen, R. Hingorani, R. Kolezynski, W.A. Lee, A. Leung, J. Lubin, H. Shvaytser, Object tracking with a moving camera,Proc. IEEE Workshop on Visual Motion, pp. 2–12, Irvine, CA, March, 1989.
S.R. Curtis and A.V. Oppenheim, Signal reconstruction from Fourier transform sign information,IEEE Trans. Acoust., Speech Sig. Process. 33(3):643–657, 1985.
L. Dreschler and H.-H. Nagel, Volumetric model and 3-D trajectory of a moving car derived from monocular TV frame sequences of a street scene,Comput. Graph. Image Process. 20:199–228, 1982.
D.J. Fleet and A.D. Jepson, Computation of component image velocity from local phase information,Intern. J. Comput. Vis. 5(1): 77–104, 1990.
K.H. Foster, J.P. Marcelja, and D.A. Pollen, Phase relationships between adjacent simple cells in the feline visual cortex,J. Physiol. Lond., vol. 345, 1983.
D. Gabor, Theory of communication,J. IEE (London) 93:429–457, 1946.
F. Glazer, G. Reynolds, and P. Anandan, Scene matching by hierarchical correlation,Proc. 1st IEEE Conf. Comput. Vis. Patt. Recog., June 1983, pp. 432–441, Washington, D.C.
W.E.L. Grimson,From Images to Surfaces: A Computational Study of the Human Early Visual System, MIT Press, Cambridge, MA, 1981.
D.J. Heeger, Optical flow using spatiotemporal filters, Intern. J. Comput. Vis. 2(4):279–302, 1987.
E.C. Hildreth,The measurement of Visual Motion, MIT Press: Cambridge, MA, 1983.
W. Hoff and N. Ahuja, Surface from stereo: integrating feature matching, disparity estimation and contour detection,IEEE Trans. Patt. Anal. Mach. Intell. 11(2):121–136, 1989.
T.S. Huang, ed.,Image Sequence Processing and Dynamic Scene Analysis, Springer-Verlag: New York, 1975.
R. Hummel, and R. Moniot, Reconstructions from zero crossings in scale space,IEEE Trans. Acous. Speech Sig. Process. 37(12):2111–2130, 1989.
B.K.P. Horn, and B.G. Schunck, Determining optical flow,Artificial Intelligence 17:185–203, 1981.
M.R.M. Jenkin, A.D. Jepson, and J.K. Tsotsos, Techniques for disparity measurement,Comput. Vis. Graph. Image Process: Graphics Models and Image Understanding. 53(1): 14–30, 1991.
A.D. Jepson and M.R.M. Jenkin, The fast computation of disparity from phase differences,Proc. IEEE Conf. Comput. Vis. Patt. Recog., San Diego, CA, pp. 398–403, June 1989.
B. Julesz, Binocular depth perception of computer-generated patterns,Bell Syst. Techn. J 39:1125–1162, 1960.
B. Julesz,Foundations of Cyclopean Perception, University of Chicago Press: Chicago, 1971.
B. Julesz, and J. Miller, Independent spatial-frequency-turned channels in binocular fusion and rivalry,Perception 4:125–143, 1975.
M. Kass, A computational framework for the visual correspondence problem,Proc. DARPA Image Understanding Workshop, Washington DC, 1983.
K. Langley, T.J. Atherton, R.G. Wilson, and M.H.E. Larcombe, Vertical and horizontal disparities from phase,Proc. 1st Europ. Conf. Comput. Vis., Autibes, France, pp. 315–325, 1990.
H.L. Lim and TO. Binford, Stereo correspondence: a hierarchical approach,Proc. DARPA Image Understanding Workshop, Los Angeles, 1987.
D. Marr and T. Poggio, A computational theory of human stereo vision,Proc. Roy. Soc. London, B. 204:301–328, 1979.
D. Marr and E. Hildreth, Theory of edge detectionProc. Roy. Soc. London B, 207:187–217, 1980.
J.E.W. Mayhew and J.P. Frisby, Psychophysical and computational studies towards a theory of human stereopsis,Artificial Intelligence 17:349–385, 1981.
H.P. Moravec, Obstacle avoidance and navigation in the real world by seeing a robot rover,Stanford Artif. Intell. Lab. Memo 340, 1980.
K.P.K. Nielson and T. Poggio, Vertical image registration in human stereopsis.MIT Artif. Intell. Memo, 743, 1983.
I. Ohta and T. Kanade, Stereo by intra- and inter-scanline search using dynamic programming,IEEE Trans. Patt. Anal. Mach. Intell., 7:139–154, 1985.
I. Ohzawa and R.D. Freeman, The binocular organization of simple cells in the cat's visual cortex,J. Neurophysiology, 56(1): 221–242, 1986.
I. Ohzawa and R.D. Freeman, The binocular organization of complex cells in the cat's visual cortex,J. Neurophysiology 56(1):243–259, 1986.
A.V. Oppenheim and J.S. Lim, The importance of phase in signals,Proc. IEEE, 69(5):529–541, 1981.
D.A. Pollen and S.F. Ronner, Spatial computation performed by simple and complex cells in the visual cortex of the cat,Vision Research 22:101–118, 1982.
G.F. Poggio and T. Poggio, The analysis and stereopsis,Ann. Rev. Neurosci. 7:379–412, 1984.
T. Poggio, V. Torre, and C. Koch, Computational vision and regularization theory,Nature, 317:638–643, 1985.
T.D. Sanger, Stereo disparity computation using Gabor filters,Biological Cybernetics 59:405–418, 1988.
H. Spitzer and S. Hochstein, Simple- and complex-cell response dependences on stimulation parameters,J. Neurophysiology 53(5):1244–1265, 1984.
T.T. Huang and J.C. Sanz, Image representation by one-bit Fourier phase: theory, sampling, and coherent image model,IEEE Trans. Acoust. Speech Sig. Process. 36(8):1292–1304, 1988.
S. Ullman,The Interpretation of Visual Motion, MIT Press: Cambridge, MA, 1979.
A.M. Waxman, An image flow paradigm,Proc. Workshop on Computer Vision: Representation and Control, Annapolis, MD, pp. 49–57, 1984.
J. Weng, N. Ahuja, and T.S. Huang, Two-view matching,Proc. 2nd Intern. Conf. Comput. Vis. Tampa, FL, pp. 64–73, 1988.
J. Weng, A theory of image matching,Proc. 3rd Intern. Conf. Comput. Vis., Osaka, Japan, pp. 200–209, 1990.
J. Weng, Signal reconstruction from windowed Fourier phase,Proc. Intern. Conf. Acoust. Speech, Sig. Process., San Francisco, CA, vol. 4, pp. 145–148, March, 1992.
J. Weng, N. Ahuja, and T.S. Huang, Matching two perspective views,IEEE Trans. Patt. Anal. Mach. Intell. 14(8):806–825, 1992.
J. Weng, Windowed Fourier phase: Completeness and signal reconstruction,IEEE Trans. Sig. Process. 41(2):657–666, 1993.
H.R. Wilson and J.R. Bergen, A four-mechanism model for threshold spatial vision,Vision Research 19:19–32, 1979.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Weng, J.(. Image matching using the windowed Fourier phase. Int J Comput Vision 11, 211–236 (1993). https://doi.org/10.1007/BF01469343
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01469343