Abstract

Unevenly distributed image illumination is a problem in an automatic machine visual inspection system used for fiber connector defect detection. This unevenly distributed illumination makes it difficult to find an appropriate horizontal threshold to convert a gray-scale image to a binary image to separate surface defects, such as blobs and scratches, from the background of the connector. This paper proposes some effective methods to compensate the unevenly distributed illumination problem so that standard image processing methods can be used effectively to detect the defects of the fiber connectors.

© 2004 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. Users’ Manual of ZX-1 Micro Connector Inspection Interferometer (Speer Fiber Optics, Hillsborough, N.J., 2000).
  2. R. T. Chin, “Automatic visual Inspection: 1981–1987,” Comput. Vision Graph. Image Process. 41, 346–381 (1998).
    [CrossRef]
  3. T. S. Newman, A. K. Jain, “A survey of automatic visual inspection,” Comput. Vision Image Understand. 61, 231–262 (1995).
    [CrossRef]
  4. B. E. Dom, V. Brecher, “Recent advances in the automatic inspection of integrated circuits for pattern defects,” Mach. Vision Appl. 8, 5–19 (1995).
    [CrossRef]
  5. B. K. P. Horn, Robot Vision (MIT Press, Cambridge, Mass., 1986), p. 187.
  6. B. K. P. Horn, “Image intensity understanding,” Artif. Intell. 8, 201–231 (1977).
    [CrossRef]
  7. P. Moon, The Scientific Basis of Illumination Engineering (Dover, New York, 1961).
  8. S. Weisberg, Applied Linear Regression, 2nd ed. (Wiley, New York, 1985)
  9. M. Jiang, “Digital image processing,” http://ct.radiology.uiowa.edu/~jiangm/courses/dip/html/dip.html .
  10. International Electrotechnical CommissionCables, Wires, Waveguides, RF Connectors, and Accessories, Communication and Signaling, IEC Standard TC46 (International Technical Commission, Geneva, Switzerland, 2003).

1998 (1)

R. T. Chin, “Automatic visual Inspection: 1981–1987,” Comput. Vision Graph. Image Process. 41, 346–381 (1998).
[CrossRef]

1995 (2)

T. S. Newman, A. K. Jain, “A survey of automatic visual inspection,” Comput. Vision Image Understand. 61, 231–262 (1995).
[CrossRef]

B. E. Dom, V. Brecher, “Recent advances in the automatic inspection of integrated circuits for pattern defects,” Mach. Vision Appl. 8, 5–19 (1995).
[CrossRef]

1977 (1)

B. K. P. Horn, “Image intensity understanding,” Artif. Intell. 8, 201–231 (1977).
[CrossRef]

Brecher, V.

B. E. Dom, V. Brecher, “Recent advances in the automatic inspection of integrated circuits for pattern defects,” Mach. Vision Appl. 8, 5–19 (1995).
[CrossRef]

Chin, R. T.

R. T. Chin, “Automatic visual Inspection: 1981–1987,” Comput. Vision Graph. Image Process. 41, 346–381 (1998).
[CrossRef]

Dom, B. E.

B. E. Dom, V. Brecher, “Recent advances in the automatic inspection of integrated circuits for pattern defects,” Mach. Vision Appl. 8, 5–19 (1995).
[CrossRef]

Horn, B. K. P.

B. K. P. Horn, “Image intensity understanding,” Artif. Intell. 8, 201–231 (1977).
[CrossRef]

B. K. P. Horn, Robot Vision (MIT Press, Cambridge, Mass., 1986), p. 187.

Jain, A. K.

T. S. Newman, A. K. Jain, “A survey of automatic visual inspection,” Comput. Vision Image Understand. 61, 231–262 (1995).
[CrossRef]

Moon, P.

P. Moon, The Scientific Basis of Illumination Engineering (Dover, New York, 1961).

Newman, T. S.

T. S. Newman, A. K. Jain, “A survey of automatic visual inspection,” Comput. Vision Image Understand. 61, 231–262 (1995).
[CrossRef]

Weisberg, S.

S. Weisberg, Applied Linear Regression, 2nd ed. (Wiley, New York, 1985)

Artif. Intell. (1)

B. K. P. Horn, “Image intensity understanding,” Artif. Intell. 8, 201–231 (1977).
[CrossRef]

Comput. Vision Graph. Image Process. (1)

R. T. Chin, “Automatic visual Inspection: 1981–1987,” Comput. Vision Graph. Image Process. 41, 346–381 (1998).
[CrossRef]

Comput. Vision Image Understand. (1)

T. S. Newman, A. K. Jain, “A survey of automatic visual inspection,” Comput. Vision Image Understand. 61, 231–262 (1995).
[CrossRef]

Mach. Vision Appl. (1)

B. E. Dom, V. Brecher, “Recent advances in the automatic inspection of integrated circuits for pattern defects,” Mach. Vision Appl. 8, 5–19 (1995).
[CrossRef]

Other (6)

B. K. P. Horn, Robot Vision (MIT Press, Cambridge, Mass., 1986), p. 187.

P. Moon, The Scientific Basis of Illumination Engineering (Dover, New York, 1961).

S. Weisberg, Applied Linear Regression, 2nd ed. (Wiley, New York, 1985)

M. Jiang, “Digital image processing,” http://ct.radiology.uiowa.edu/~jiangm/courses/dip/html/dip.html .

International Electrotechnical CommissionCables, Wires, Waveguides, RF Connectors, and Accessories, Communication and Signaling, IEC Standard TC46 (International Technical Commission, Geneva, Switzerland, 2003).

Users’ Manual of ZX-1 Micro Connector Inspection Interferometer (Speer Fiber Optics, Hillsborough, N.J., 2000).

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 (10)

Fig. 1
Fig. 1

Sample image of a fiber connector.

Fig. 2
Fig. 2

Thresholds selection in an ideal case.

Fig. 3
Fig. 3

Intensity profile and the best linear fit along the horizontal diameter.

Fig. 4
Fig. 4

Three-dimensional intensity profile map of the tilt-corrected image.

Fig. 5
Fig. 5

Image of the first sample after tilt correction.

Fig. 6
Fig. 6

Image of the second sample.

Fig. 7
Fig. 7

Three-dimensional nonlinear intensity map of the second sample image.

Fig. 8
Fig. 8

Image profiles at different stages of image processing.

Fig. 9
Fig. 9

Final image with linear and nonlinear compensation.

Fig. 10
Fig. 10

Three-dimensional intensity map of the second sample image after nonlinear compensation.

Equations (8)

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

bx, y=rx, yex, y
Ix, y=c+ε,
Ix, y=c+dx, y+ε.
Ix, y=c+dx, y+Lx, y+ε.
b=i=1m ziIi-i=1m zii=1m Iimi=1m zi2-i=1m zii=1m zim,
a=i=1m Ii-b i=1m zim.
Ix, y=c+dx, y+Nx, y+ε.
nxi+j, yi+k=1-t1-unxi, yi+t1-unxi+m, yi+u1-tnxi, yi+m+tu nxi+m, yi+m,

Metrics