Abstract
We describe a complete system for quantitatively measuring the optical distortion in aircraft windshields and automatically classifying that distortion as acceptable or not. The system comprises two parts: The first uses digital imaging of a known grid pattern through the windshield of interest to create a distortion map of that windshield; the second uses the distortion maps created for 100 windshields (some acceptable and some not) and automatically learns a decision-tree-based classifier. We show results that highlight the robustness of this system, including a demonstration that the distortion map for a windshield is consistently measured over 3 years, and cross-validation study shows that we can effectively classify windshields based on the distortion maps.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amosov N.I.: Estimating the optical distortion from curved automobile glass. Glass Ceram. 15(8), 427 (1960)
Barbato, M.H., Kama, W.N., Task, H.L., Hausmann, M.A., Bridenbaugh, J.C.: Definitions of terms relating to aircraft windscreens, canopies, and transparencies. Tech. rep., Defense Technical Information Center OAI-PMH Repository (United States) (1998)
Breiman L., Friedman J., Stone C.J., Olshen R.A.: Classification and Regression Trees. Chapman & Hall/CRC, Boca Raton (1984)
Freeman, P., Gleason, M.P., Thomas, M.M., Dixon, M., Pless, R., Smart, W.D.: Evaluation of optical distortion in a transparency (2006). Patent pending
Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. 28 (1998)
Harris, J.S., Harding, K.G., Mersch, S.H.: Techniques for evaluation of aircraft windscreen optical distortion. Optical Engineering 20, 115–122 (1981)
Joachims, T.: Making large-scale support vector machine learning practical. Advances in Kernel Methods: Support Vector Learning, pp. 169–184. MIT Press, Cambridge (1999)
Kama, W.: Measures of distortion: Are they relevant? In: Marulo, S.A. (ed.) Proceedings of the Conference on Aerospace Transparent Materials and Enclosures, vol. II, pp. 1073–1093. Wright Research and Development Center, Wright-Patterson AFB, OH (1989)
Mccullagh P., Nelder J.: Generalized Linear Models. Chapman & Hall/CRC, Boca Raton (1990)
Miyake, A., Matsushita, Y., Koyama, T.: System of detecting optical distortion of a light-transmitting plate-like member. US Patent 5446536 (1995).
Quinlan R.J.: C4.5: Programs for Machine Learning (Morgan Kaufmann Series in Machine Learning). Morgan Kaufmann, San Francisco (1993)
Schave, R.D.: Method and apparatus for inspection and evaluation of angular deviation and distortion defects for transparent sheets. US Patent 5726749 (1998)
Self, H.C., Task, H.L.: Potential of optical fourier analysis for measuring windscreen distortion. Tech. Rep. ADA094127, Air Force Aerospace Medical Research Lab Wright-Patterson AFB, OH (1980)
Task, H.L., Genco, L.V., Smith, K.L., Dabbs, A.G.: System for measuring angular deviation in a transparency. US Patent 4377341 (1983)
Thomas, M.M., Gleason, M.P., Freeman, P.L., Dixon, M., Pless, R., Smart, W.D.: High-resolution digital photography in transparency optical distortion detection. In: ASTM F7.08 Annual Meeting on Aircraft Transparencies, Atlanta, GA (2006)
Vapnik V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Dixon, M., Glaubius, R., Freeman, P. et al. Measuring optical distortion in aircraft transparencies: a fully automated system for quantitative evaluation. Machine Vision and Applications 22, 791–804 (2011). https://doi.org/10.1007/s00138-010-0258-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-010-0258-z