Structural Synthesis based on PCA: Methodology and Evaluation

Sriniwas Chowdhary Maddukuri, Wolfgang Heidl, Christian Eitzinger, Andreas Pichler

2016

Abstract

In recent surface inspections systems, interactive training of fault classification is becoming state of the art. While being most informative for both training and explanation, fault samples at the decision boundary are rare in production datasets. Therefore, augmenting the dataset with synthesized samples at the decision boundary could greatly accelerate the training procedure. Traditionally, synthesis methods had proven to be useful for computer graphics applications and have only been applied for generating samples with stochastic and regular texture patterns. Presently, the state of the art synthesis methods assume that the test sample is available and are feature independent. In the context of surface inspection systems, incoming samples are often classified to several defect classes after the feature extraction stage. Therefore, the goal in this research work is to perform the synthesis for a new feature vector such that the resulting synthesized image visualizes the decision boundary. This paper presents a methodology for structural synthesis based on principal components analysis. The methodology expects the samples of the training set as an input. It renders the synthesized form of the input samples of training set through eigenimages and its computed coefficients by solving a linear regression problem. The methodology has been evaluated on an industrial dataset to validate its performance.

References

  1. Heeger, D.J., Bergen, J.R., Moore, R., 1995. Pyramidbased texture analysis/synthesis. In SIGGRAPH'95, Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques, pp. 229-238, New York, USA.
  2. Portilla, J., Simoncelli, E.P., 2000. A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients. International Journal of Computer Vision - Special issues on Statistical and Computational Theories of Vision: Modelling, learning, sampling and computing, vol. 40, issue 1, pp. 49-70.
  3. Balsa, B.J., 2006. Texture synthesis and perception: Using computational models to study texture representations in the human visual system. Vision Research, vol. 46, issue 3, pp. 299-309, PERGAMON.
  4. Balas, B.J., Nakano, L., Rosenholtz, R., 2009. A summary-statistic representation in peripheral vision explains visual crowding. Journal of Vision, vol. 9, issue 12, pp. 1-18.
  5. Efros, A. A., Leung, T.K., “Texture synthesis by nonparametric sampling”, in Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, vol. 2, no., pp. 1033-1038, 1999.
  6. Wei, L.-Y., Levoy, M., 2000. Fast texture synthesis using tree-structures vector quantization. In SIGGRAPH'00, Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 479-488.
  7. Kwatra, V., Essa, I., Bobick, K.A., Kwatra, N., 2005. Texture optimization for example-based synthesis. In SIGGRAPH'05, Proceedings of ACM SIGGRAPH 2005, vol. 24, issue 3. pp. 795-802.
  8. Zelinka, S., Garland, M., 2004. Jump map-based interactive texture synthesis. ACM Transactions on Graphics, vol. 23, issue 4, pp. 930-962.
  9. Tong, X., Zhang, J., Liu, L., Wang, X., Shum, H.-Y, 2002. Synthesis of bidirectional texture functions on arbitrary surfaces. In SIGGRAPH'02, Proceedings of ACM SIGGRAPH 2002, vol. 21, issue 3, pp. 665-672.
  10. Thumfart, S., “PhD Thesis: Genetic Texture Synthesis”, Johannes Kepler University Linz, Department of Computational Perception, 2012.
  11. Guo, H., Ono, N., Sagayama, S., 2008. A StructureSynthesis Image Inpainting Algorithm based on Morphological Erosion Operation. In CISP'08, Proceedings of the 2008 Congress on Image and Signal Processing, vol. 3, issue 27 - 30, pp. 530 - 535.
  12. Xiaowu, Chen., Fang, Xu., 2010. Automatic Image Inpainting by Heuristic Texture and Structure Completion. In MMM'10, Proceedings of the 16th International Conference on Advances in Multimedia Modelling, pp. 110 - 119.
  13. Belhumeur, P.N., Hespanha, J.P., Kriegman, D., “Eigenfaces vs Fisherfaces: Recognition Using Class Specific Linear Projection”, in Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 19, no. 7, pp. 711-720, July 1997.
  14. Turk, M., Pentland, A.P., “Face recognition using eigenfaces”, in Computer Vision and Pattern Recognition, 1991. IEEE Computer Society Conference on, vol., no., pp. 586-591, 3-6 June 1991.
  15. Noortiawati, T. M. D., Hussain, A., Samad, S.A., Hussain, H., Marzuki, M. M., 2006. Eigenposture for Classification. Journal of Applied Science, vol. 6, issue 2, pp. 419-424.
  16. Hastie, T., Tibshirani, R., Friedman, J., 2001. The Elements of Statistical Learning, Springer New York Inc., New York, 2nd edition.
  17. Friedman, J., Tibshirani, R., Hastie, T., 2010. Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software. vol. 33, no. 1, URL: http://www.jstatsoft.org/v33/i01.
  18. Qian, J., Hastie, T., Friedman, J., Tibshirani, R., Simon, N., 2013. Glmnet for Matlab. URL: http://www.stanford.edu/hastie/glmnet_matlab/ Weigl, E., Heidl, W., Lughofer, E., Radauer, T., Eitzinger, C., 2014. On Improving Performance of Surface Inspection Systems by On-line Active Learning and Flexible Classifier Updates. In MACH VISION
Download


Paper Citation


in Harvard Style

Maddukuri S., Heidl W., Eitzinger C. and Pichler A. (2016). Structural Synthesis based on PCA: Methodology and Evaluation . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 348-355. DOI: 10.5220/0005721403480355


in Bibtex Style

@conference{visapp16,
author={Sriniwas Chowdhary Maddukuri and Wolfgang Heidl and Christian Eitzinger and Andreas Pichler},
title={Structural Synthesis based on PCA: Methodology and Evaluation},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={348-355},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005721403480355},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - Structural Synthesis based on PCA: Methodology and Evaluation
SN - 978-989-758-175-5
AU - Maddukuri S.
AU - Heidl W.
AU - Eitzinger C.
AU - Pichler A.
PY - 2016
SP - 348
EP - 355
DO - 10.5220/0005721403480355