Abstract

A method has been devised to accomplish contrast-invariant pattern recognition using multiple circular harmonic components. In addition to detecting targets with various contrasts in the presence of high-contrast objects, the method is shift- and rotation-invariant. A vector f is formed from the autocorrelation values for each member of a set of circular harmonic components corresponding to the target of interest. The unit vector f/f is a feature vector whose direction characterizes the target. Target detection is accomplished by comparing the corresponding cross-correlation unit vector to the vector f/f. Experimental results are shown.

© 1985 Optical Society of America

Full Article  |  PDF Article

Corrections

Henri H. Arsenault and Claude Belisle, "Contrast-invariant pattern recognition using circular harmonic components," Appl. Opt. 24, 3304-3304 (1985)
https://www.osapublishing.org/ao/abstract.cfm?uri=ao-24-19-3304

References

  • View by:
  • |
  • |
  • |

  1. Y.-N. Hsu, H. H. Arsenault, G. April, “Rotation-Invariant Digital Pattern Recognition Using Circular Harmonic Expansion,” Appl. Opt. 21, 4012 (1982).
    [CrossRef] [PubMed]
  2. H. H. Arsenault, Y. N. Hsu, K. Chalasinska-Macukow, “Rotation-Invariant Pattern Recognition,” Opt. Eng. 23, 705 (1984).
    [CrossRef]
  3. Y.-N. Hsu, H. H. Arsenault, “Pattern Discrimination by Multiple Circular Harmonic Components,” Appl. Opt. 23, 841 (1984).
    [CrossRef] [PubMed]
  4. R. Wu, H. Stark, “Rotation-Invariant Pattern Recognition Using a Vector Reference,” Appl. Opt. 23, 838 (1984).
    [CrossRef] [PubMed]
  5. A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory IT-10, 139 (1964).
    [CrossRef]
  6. Y.-N. Hsu, H. H. Arsenault, “Statistial Performance of the Circular Harmonic Filter for Rotation-Invariant Pattern Recognition,” Appl. Opt. 22, 2804 (1983).
    [CrossRef] [PubMed]
  7. R. Wu, H. Stark, “Rotation-Invariant Image Pattern Recognition Using Circular Harmonic Functions and Optimum Feature Extraction,” J. Opt. Soc. Am. A 1, 1302A (1984).

1984 (4)

H. H. Arsenault, Y. N. Hsu, K. Chalasinska-Macukow, “Rotation-Invariant Pattern Recognition,” Opt. Eng. 23, 705 (1984).
[CrossRef]

R. Wu, H. Stark, “Rotation-Invariant Image Pattern Recognition Using Circular Harmonic Functions and Optimum Feature Extraction,” J. Opt. Soc. Am. A 1, 1302A (1984).

R. Wu, H. Stark, “Rotation-Invariant Pattern Recognition Using a Vector Reference,” Appl. Opt. 23, 838 (1984).
[CrossRef] [PubMed]

Y.-N. Hsu, H. H. Arsenault, “Pattern Discrimination by Multiple Circular Harmonic Components,” Appl. Opt. 23, 841 (1984).
[CrossRef] [PubMed]

1983 (1)

1982 (1)

1964 (1)

A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory IT-10, 139 (1964).
[CrossRef]

April, G.

Arsenault, H. H.

Chalasinska-Macukow, K.

H. H. Arsenault, Y. N. Hsu, K. Chalasinska-Macukow, “Rotation-Invariant Pattern Recognition,” Opt. Eng. 23, 705 (1984).
[CrossRef]

Hsu, Y. N.

H. H. Arsenault, Y. N. Hsu, K. Chalasinska-Macukow, “Rotation-Invariant Pattern Recognition,” Opt. Eng. 23, 705 (1984).
[CrossRef]

Hsu, Y.-N.

Stark, H.

R. Wu, H. Stark, “Rotation-Invariant Pattern Recognition Using a Vector Reference,” Appl. Opt. 23, 838 (1984).
[CrossRef] [PubMed]

R. Wu, H. Stark, “Rotation-Invariant Image Pattern Recognition Using Circular Harmonic Functions and Optimum Feature Extraction,” J. Opt. Soc. Am. A 1, 1302A (1984).

Vander Lugt, A.

A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory IT-10, 139 (1964).
[CrossRef]

Wu, R.

R. Wu, H. Stark, “Rotation-Invariant Image Pattern Recognition Using Circular Harmonic Functions and Optimum Feature Extraction,” J. Opt. Soc. Am. A 1, 1302A (1984).

R. Wu, H. Stark, “Rotation-Invariant Pattern Recognition Using a Vector Reference,” Appl. Opt. 23, 838 (1984).
[CrossRef] [PubMed]

Appl. Opt. (4)

IEEE Trans. Inf. Theory (1)

A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory IT-10, 139 (1964).
[CrossRef]

J. Opt. Soc. Am. A (1)

R. Wu, H. Stark, “Rotation-Invariant Image Pattern Recognition Using Circular Harmonic Functions and Optimum Feature Extraction,” J. Opt. Soc. Am. A 1, 1302A (1984).

Opt. Eng. (1)

H. H. Arsenault, Y. N. Hsu, K. Chalasinska-Macukow, “Rotation-Invariant Pattern Recognition,” Opt. Eng. 23, 705 (1984).
[CrossRef]

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (4)

Fig. 1
Fig. 1

Input image containing four target letters E with different orientations.

Fig. 2
Fig. 2

Positions of detected targets in Fig. 1 with the vector difference method using (a) proper centers and (b) a unique center.

Fig. 3
Fig. 3

Input image similar to Fig. 1 but with targets having contrasts equal to 1.0, 0.8, 0.6, and 0.4.

Fig. 4
Fig. 4

Positions of detected targets in Fig. 3 with the vector orientation method using (a) proper centers and (b) a unique center.

Tables (4)

Tables Icon

Table I Relative Values of the Correlation Intensities of Fig. 2(a) (Proper Centers) and Fig. 2(b) (Unique Center) for the Vector Difference Method

Tables Icon

Table II Relative Values of the Correlation Intensities of Fig. 4(a) (Proper Centers) and Fig. 4(b) (Unique Center) for the Vector Difference Method

Tables Icon

Table III Intensities and Scalar Products Found by the Vector Orientation Method for the Targets of Fig. 1

Tables Icon

Table IV Intensities and Scalar Products Found by the Vector Orientation Method for the Targets of Fig. 3

Equations (12)

Equations on this page are rendered with MathJax. Learn more.

f ( r , ϕ ) = 0 f M ( r ) exp ( j M ϕ ) ,
f M ( r ) = ½ π 0 2 π f ( r , ϕ ) exp ( j M ϕ ) d ϕ .
R f f ( r , ϕ ) = f ( x , y ) f * ( x x , y y ) d x d y ,
R f f ( 0 , 0 ) = 0 [ f M ( 0 ) ] 2 .
g < t ,
D = f g .
f g < T ,
f ̂ g ̂ > T .
f ̂ g ̂ < T ,
| f i | < T i
f ̂ g ̂
f ̂ g ̂

Metrics