Fast template matching based on the normalized correlation by using multiresolution eigenimages

@inproceedings{Yoshimura1994FastTM,
  title={Fast template matching based on the normalized correlation by using multiresolution eigenimages},
  author={Shinichi Yoshimura and Takeo Kanade},
  booktitle={IROS},
  year={1994}
}
We present a fast computation method of the normalized correlation for multiple rotated templates by using multiresolution eigenimages. This method allows us to accurately detect both location and orientation of the object in a scene a t faster rate than applying conventional template matching to the rotated object. Since the correlation among slightly rotated templates is high, we first apply the Karhunen-LoCve expansion to a set of rotated templates and extract "eigenimages" from them. Each… CONTINUE READING
Highly Cited
This paper has 60 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 39 extracted citations

61 Citations

0510'96'01'07'13
Citations per Year
Semantic Scholar estimates that this publication has 61 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-6 of 6 references

Application of the karhunen - loCve procedure for the characterisation of humen facea

  • L. Sirovich
  • J . Opt . Soc . Amer . A
  • 1987

Efficient calcula tion of primary images from a set of images , " IEEE naris

  • E. H. Adelson, C. M. Brown
  • 1982

" Template matching in pyramids

  • S. L. Tanimoto
  • Comput . Graphics Images Processing
  • 1981

, " A hierarchical data structure for picture processing

  • T. Pavlidis
  • Comput . Graphics Images Processing

Parametric eigenspace representation for visual learning and recognition

  • A. P. Pentland

Similar Papers

Loading similar papers…