Abstract
We propose a coupled hidden Markov model (CHMM) for analysis of steel surfaces containing three-dimensional flaws. The aim is to model surface errors, which are stretched across one or more surface segments because of their strongly varying size. Due to scale on the surface, the reflection property across the intact surface changes and intensity imaging fails. Light sectioning is used to acquire the surface range data. The steel block is vibrating on the conveyor during data acquisition, which complicates robust feature extraction. After depth map recovery and feature extraction, segments of the surface are classified using CHMMs. The CHMM achieves a recognition rate of 98.57%. We compare the CHMM approach to the naïve Bayes classifier, the Hidden Markov Model, the k-nearest neighbor classifier, and to the Support Vector Machine.
Similar content being viewed by others
References
Newman, T., Jain, A.: A survey of automated visual inspection. Comput. Vision Image Understand. 61(2), 231–262 (1995)
Pernkopf, F., O'Leary, P.: Image acquisition techniques for automatic visual inspection of metallic surfaces. NDT E Int. 36(8), 609–617 (2003)
Dupont, F., Odet, C., Carton, M.: Optimization of the recognition of defects in flat steel products with the cost matrices theory. NDT N Int. 30(1), 3–10 (1997)
Pernkopf, F., O'Leary, P.: Visual inspection of machined metallic high-precision surfaces, special issue on applied visual inspection. EURASIP J. Appl. Signal Process. (7), 667–678 (2002)
Nayar, S., Ikeuchi, K., Kanade, T.: Surface reflection: physical and geometrical perspectives. IEEE Trans. Pattern Anal. Machine Intell. 13(7), 611–634 (1991)
Torrance, K., Sparrow, E.: Theory for off-specular reflection from roughened surfaces. J. Optical Soc. Am. 57(9), 1105–1114 (1967)
Proceedings of SPIE. Machine Vision Applications in Industrial Inspection. URL: www.spie.org
Kanade, R.: Three-Dimensional Machine Vision. Kluwer Academic Publishers, Drodrecht (1987)
Curless, B., Levoy, M.: Better optical triangulation through spacetime analysis. In: 5th International Conference on Computer Vision, pp. 987–994 (1995)
IVP (Integrated Vision Products), Company. IVP Ranger SAH5 Product Information. URL: www.ivp.se.
Brand, M., Oliver, N., and Pentland, A.: Coupled hidden markov models for complex action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 994–999 (1997)
Nefian, A.: Embedded Bayesian networks for face recognition. In: IEEE International Conference on Multimedia and Expo, vol. 2, pp. 133–136 (2002)
Nefian, A., Liang, L., Pi, X., Liu, X., Murphy, K.: Dynamic Bayesian networks for audio-visual speech recognition. EURASIP J. Appl. Signal Process. 11, 1–15 (2002)
Long, A., Long, C.: Surface approximation and interpolation via matrix SVD. College Math. J. 32(1), 20–25 (2001)
Golub, G., Loan, C.V.: Matrix Computations, 3rd ed. The John Hopkins University Press (1996)
Pernkopf, F., Pernkopf, F., O'Leary, P.: Detection of surface defects on raw milled steel blocks using range imaging. In: IT&S/SPIE 14th Symposium Electronic Imaging, pp. 170–181 (2002)
Pernkopf, F.: Detection of surface defects on raw steel blocks using Bayesian network classifiers. Pattern Anal. Appl. 7(3), 333–342 (2004)
Gonzalez, R., Woods, R.: Digital Image Processing. Addison-Wesley, Reading (1992)
McLachlan, G., Peel, D.: Fintite Mixture Models. Wiley, New York (2000)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood estimation from incomplete data via the EM algorithm. J. R. Stat. Soc. 30(B), 1–38 (1977)
Pavlovic, V.: Dynamic Bayesian networks for information fusion with applications to human–computer interfaces. PhD thesis, University of Illinois at Urbana-Champaign (1999)
Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley, New York (2000)
Burges, C.: A tutorial on support vector machines for pattern recognition. Data Min. Knowledge Discov. 2(2), 121–167 (1998)
Schölkopf, B., Smola, A.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press (2001)
Author information
Authors and Affiliations
Corresponding author
Additional information
Franz Pernkopf received his MSc (Dipl. Ing.) degree in Electrical Engineering at Graz University of Technology, Austria, in summer 1999. He earned a PhD degree from the University of Leoben, Austria, in 2002. In 2002 he was awarded the Erwin Schrödinger Fellowship. In 2004 he was a research associate at the Department of Electrical Engineering at the University of Washington, Seattle. Currently, he is an university assistant at the Signal Processing and Speech Communication Laboratory at Graz University of Technology, Austria. His research interests include graphical models, generative and discriminative learning of Bayesian network classifiers, feature selection, finite mixture models, image processing and vision, and statistical pattern recognition.
Rights and permissions
About this article
Cite this article
Pernkopf, F. 3D surface analysis using coupled HMMs. Machine Vision and Applications 16, 298–305 (2005). https://doi.org/10.1007/s00138-005-0001-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-005-0001-3