9.5 Conclusion
We proposed a method for detection of surface defects on wooden boards. This method uses a set of Gabor filters, whose output is combined and thresholded, followed by morphological processing for the detection of line like objects. We used a genetic algorithm to compute an optimal set of parameters for the various processing steps. The optimisation was done by generating a set of candidate parameter sets and changing them in an iterative manner such that the overall fitness function improved. Fitness was measured in terms of deviations from the desired output of the detection result. The method was found to be a feasible approach to the underlying training problem. With the genetic algorithm, the training step can now run with very little operator intervention. Future work in the proposed direction will focus on the application of a similar procedure to detect other surface defects on wooden boards, especially texture classification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
9.6 References
Polzleitner W., Schwingshakl G. (1992) Real-time surface grading of profiled board, Industrial Metrology, vol. 2, nos. 3 & 4, pp. 283–298.
Polzleitner W., Schwingshakl G. (1994) Argus: a flexible real-time system for 2d defect and texture classification of wooden material, Optics in Agriculture, Forestry, and Biological Processing, Proc. SPIE, Vol. 2345.
Polzleitner W. (1993) Convex shape refinement using dynamic programming for surface defect classification on wooden materials, Optical Tools for Manufacturing and Advanced Automation, Intelligent Robots and Computer Vision XII: Algorithms and Techniques, (Boston), Proc. SPIE Vol. 2055.
Shenoy R., Casasent D. (1995) Fast non-dyadic shift-invariant gabor wavelet, (Orlando, FL.), Proc. SPIE-Int. Soc. Opt. Eng. (USA).
Casasent D., Ye A., Smokelin J.S., Schaefer R. (1994) Optical correlation filter fusion for object detection, Opt. Eng., Vol. 33,No. 6, pp. 1757–1766.
Casasent D., Smokelin J.S. (1994) Real, imaginary, and clutter gabor filter fusion for detection with reduced false alarm, Optical Engineering, Vol. 33,No. 7, pp. 2255–2263.
Casasent D., Smokelin J.S. (1994) Neural net design of macro gabor wavelet filters for distortion-invariant object detection in clutter, Optical Engineering, Vol. 33,No. 7, pp. 2264–2271.
Casasent D., Smokelin J.S., Ye A. (1992) Wavelet and gabor transforms for detection, Optical Engineering, Vol. 31,No. 9, pp. 1893–1898.
Hubel D., Wiesel T. (1962) Receptive fields, binocular interaction, and functional architecture in the cats visual cortex, J. Physiol. London, Vol. 160, pp. 106–154.
Campbell F., Cooper G., and Enroth-Cugell C. (1969) The spatial selectivity of the visual cells of the cat, J. Physiol. London, Vol. 203, pp. 223–235.
Campbell F., Robson J. (1968) Application of fourier analysis to the visiblity of grating, J. Physiol. London, Vol. 160, pp. 551–566.
Gabor D. (1946) Theory of communication, J. IEE, Vol. 93, pp. 429–457.
Daugman J. (1980) Two-dimensional spectral analysis of cortical receptive field profiles, Vision Research, Vol. 20, pp. 847–856.
Casasent D., Smokelin J.S. (1994) Real, imaginary, and clutter gabor filter fusion for detection with reduced false alarm, Optical Engineering, Vol. 33,No. 7, pp. 2255–2263.
Goldberg D. (1989) Genetic Algorithms in Serach, Optimization, and Machine Learning,. Reading, MA.: Addison-Wesley.
Pözleitner W., Casasent D. (1996) A unified approach to control point detection and stereo disparity computation, Intelligent Robots and Computer Vision XV: Algorithms, Techniques, Active Vision, and Materials Handling, Vol. 2904-24, (Boston), SPIE.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag London Limited
About this chapter
Cite this chapter
Pölzleitner, W. (2003). Quality Classification of Wooden Surfaces Using Gabor Filters and Genetic Feature Optimisation. In: Graves, M., Batchelor, B. (eds) Machine Vision for the Inspection of Natural Products. Springer, London. https://doi.org/10.1007/1-85233-853-9_9
Download citation
DOI: https://doi.org/10.1007/1-85233-853-9_9
Publisher Name: Springer, London
Print ISBN: 978-1-85233-525-0
Online ISBN: 978-1-85233-853-4
eBook Packages: Springer Book Archive