Abstract
Classification of detected events is a central component in state-of-the-art surface inspection systems that still relies on manual parametrization. While machine-learned classifiers promise supreme accuracy, their reliability depends on complete and correct annotation of an extensive training database, leaving the risk of unpredictable behavior in changing production environments. We propose an active learning-based training framework, which selectively presents questionable events for user annotation and is capable of online operation. Evaluation results on two data streams from microfluidic chips and elevator sheaves production show that annotation effort can be reduced by 90 % with negligible loss of accuracy. Simulation runs introducing new event classes show that the online active learning procedure is both efficient in terms of learning speed and robust in maintaining the accuracy levels of existing classes. The results underline the feasibility and potential of our approach that significantly reduces the required effort for inspection system setup and adapts to changes in the production process.
Similar content being viewed by others
References
Angelov, P., Lughofer, E., Zhou, X.: Evolving fuzzy classifiers using different model architectures. Fuzzy Sets Syst. 159(23), 3160–3182 (2008)
Belohlavek, R.: Fuzzy Relational Systems. Springer, Heidelberg, Berlin (2002)
Bifet, A., Holmes, G., Kirkby, R., Pfahringer, B.: Data stream mining—a practical approach. Technical report, Department of Computer Sciences, University of Waikato, Japan (2011)
Bifet, A., Kirkby, R.: Data stream mining—a practical approach. Technical report, Department of Computer Sciences, University of Waikato, Japan (2011)
Bordes, A., Ertekin, S., Weston, J., Bottou, L.: Fast kernel classifiers with online and active learning. J. Mach. Learn. Res. 6, 1579–1619 (2005)
Bouchachia, A.: Incremental induction of classification fuzzy rules. In: IEEE Workshop on Evolving and Self-Developing Intelligent Systems (ESDIS) 2009, Nashville, USA, pp. 32–39 (2009)
Brazdil, P., Giraud-Carrier, C., Soares, C., Vilalta, R.: Metalearning. Springer, Berlin, Heidelberg (2009)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. Chapman and Hall, Boca Raton (1993)
Brinkmann, R.: The Art and Science of Digital Compositing. Morgan Kaufmann, San Francisco (1999)
Caleb-Solly, P., Smith, J.E.: Adaptive surface inspection via interactive evolution. Image Vis. Comput. 25(7), 1058–1072 (2007)
Chapelle, O., Schoelkopf, B., Zien, A.: Semi-Supervised Learning. MIT Press, Cambridge (2006)
Cheng, J., Wang, K.: Active learning for image retrieval with co-svm. Pattern Recognit. 40, 330–334 (2006)
Cheng, Y., Chen, Z., Liu, L., Wang, J., Agrawal, A., Choudhary, A.: Feedback-driven multiclass active learning for data streams. In: Proceedings of the 22nd ACM International Conference on Information and Knowledge management, CIKM ’13, pp. 1311–1320. ACM, New York (2013)
Chu, W., Zinkevich, M., Li, L., Thomas, A., Zheng, B.: Unbiased online active learning in data streams. In: Proceedings of the KDD 2011, San Diego, California (2011)
Dean, J.: Big Data, Data Mining, and Machine Learning: Value Creation for Business Leaders and Practitioners. Wiley, Hoboken (2012)
Demant, C., Streicher-Abel, B., Waszkewitz, P.: Industrial Image Processing: Visual Quality Control in Manufacturing. Springer, Berlin, Heidelberg (1999)
Donmez, P., Carbonell, J.G.: From active to proactive learning methods. In: Kornoacki, J., Ras, Z.W., Wierzchon, S.T., Kacprzyk, J. (eds.) Advances in Machine Learning Part I. Studies in Computational Intelligence, vol. 262, pp. 97–120. Springer, Berlin, Heidelberg (2010)
Donmez, P., Carbonell, J.G., Bennett, P.N.: Dual strategy active learning. In: Kornoacki, J., Lopez de Mantaras, R., Matwin, S., Mladenic, D., Skowron, A. (eds.) Proceedings of the ECML 2007 Conference. LNCS (LNAI), vol. 4701, pp. 116–127. Springer, Heidelberg (2007)
Efron, B., Tibshirani, R.: An Introduction to the Bootstrap. Chapman and Hall/CRC, Boca Raton (1993)
Efron, B., Tibshirani, R.: Improvements on cross-validation: the 632 + bootstrap method. J. Am. Stat. Assoc. 92(438), 548–560 (1997)
Eitzinger, C., Heidl, W., Lughofer, E., Raiser, S., Smith, J.E., Tahir, M.A., Sannen, D., Van Brussel, H.: Assessment of the influence of adaptive components in trainable surface inspection systems. Mach. Vis. Appl. 21(5), 613–626 (2009)
Fürnkranz, J.: Round robin classification. J. Mach. Learn. Res. 2, 721–747 (2002)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd edn. Springer, New York, Berlin, Heidelberg (2009)
Heidl, W., Thumfart, S., Lughofer, E., Eitzinger, C., Klement, E.-P.: Machine learning based analysis of gender differences in visual inspection decision making. Inf. Sci. 224, 62–76 (2013)
Hu, W., Hu, W., Xi, N., Maybank, S.: Unsupervised active learning based on hierarchical graph-theoretic clustering. IEEE Trans. Syst. Man Cybern. Part B: Cybern. 39(5), 1147–1161 (2009)
Hua, G., Long, C., Yang, M., Gao, Y.: Collaborative active learning of a kernel machine ensemble for recognition. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 1209–1216, Dec (2013)
Hühn, J., Hüllermeier, E.: FR3: a fuzzy rule learner for inducing reliable classifiers. IEEE Trans. Fuzzy Syst. 17(1), 138–149 (2009)
Hüllermeier, E., Brinker, Klaus: Learning valued preference structures for solving classification problems. Fuzzy Sets Syst. 159(18), 2337–2352 (2008)
Joshi, A.J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2372–2379. IEEE Press (2009)
Kim, C.W., Koivo, A.J.: Hierarchical classification of surface defects on dusty wood boards. Pattern Recognit. Lett. 15(7), 713–721 (1994)
Krishnamoorthy, K., Mathew, T.: Statistical Tolerance Regions: Theory, Applications, and Computation. Wiley, Hoboken (2009)
Kuncheva, L.: Fuzzy Classifier Design. Physica-Verlag, Heidelberg (2000)
Kuncheva, L.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience (Wiley), Southern Gate, Chichester (2004)
Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: Proceedings of the 11th International Conference on Machine Learning, New Brunswick, New Jersey, pp. 148–156 (1994)
Li, X., Wang, L., Sung, E.: Multilabel SVM active learning for image classification. In: Proceedings of the International Conference on Image Processing (ICIP), Singapore, vol. 4, pp. 2207–2010 (2004)
Long, C., Hua, G., Kapoor, A.: Active visual recognition with expertise estimation in crowdsourcing. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 3000–3007, Dec (2013)
Loy, C.C., Hospedales,T.M., Xiang, T., Gong, S.: Stream-based joint exploration-exploitation active learning. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1560–1567, June (2012)
Lughofer, E.: Extensions of vector quantization for incremental clustering. Pattern Recognit. 41(3), 995–1011 (2008)
Lughofer, E.: On-line evolving image classifiers and their application to surface inspection. Image Vis. Comput. 28(7), 1065–1079 (2010)
Lughofer, E.: On-line assurance of interpretability criteria in evolving fuzzy systems—achievements, new concepts and open issues. Inf. Sci. 251, 22–46 (2013)
Lughofer, E., Buchtala, O.: Reliable all-pairs evolving fuzzy classifiers. IEEE Trans. Fuzzy Syst. 21(4), 625–641 (2013)
Lughofer, E., Eitzinger, C., Guardiola, C.: On-line quality control with flexible evolving fuzzy systems. In: Sayed-Mouchaweh, M., Lughofer, E. (eds.) Learning in Non-Stationary Environments: Methods and Applications, pp. 375–406. Springer, New York (2012)
Lughofer, E., Smith, J.E., Tahir, M.A., Caleb-Solly, P., Eitzinger, C., Sannen, D., Nuttin, M.: Human–machine interaction issues in quality control based on on-line image classification. IEEE Trans. Syst. Man Cybern. Part A: Syst. Hum. 39(5), 960–971 (2009)
Nauck, D., Kruse, R.: NEFCLASS-X—a soft computing tool to build readable fuzzy classifiers. BT Technol. J. 16(3), 180–190 (1998)
Pratama, M., Anavatti, S.G., Angelov, P., Lughofer, E.: PANFIS: a novel incremental learning machine. IEEE Trans. Neural Netw. Learn. Syst. 25(1), 55–68 (2014)
Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, San Francisco (1993)
Raghavan, H., Madani, O., Jones, R.: Active learning with feedback on both features and instances. J. Mach. Learn. Res. 7, 1655–1686 (2006)
Raiser, S., Lughofer, E., Eitzinger, C., Smith, J.E.: Impact of object extraction methods on classification performance in surface inspection systems. Mach. Vis. Appl. 21(5), 627–641 (2010)
Ravikumara, S., Ramachandran, K.I., Sugumaran, V.: Machine learning approach for automated visual inspection of machine components. Expert Syst. Appl. 38(4), 3260–3266 (2011)
Rodrigues, F., Pereira, F., Ribeiro, B.: Gaussian process classification and active learning with multiple annotators. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14), pp. 433–441 (2014)
Saffari, A., Leistner, C., Santner, J., Godec, M., Bischof, H.: On-line random forests. In: 2009 IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1393–1400 (2009)
Sannen, D., van Brussel, H.: A multilevel information fusion approach for visual quality inspection. Inf. Fusion 13(1), 48–59 (2012)
Schoonahd, J.W., Gould, J.D., Miller, L.A.: Studies of visual inspection. Ergonomics 16(4), 365–379 (1973)
Sculley, D.: Online active learning methods for fast label efficient spam filtering. In: Proceedings of the Fourth Conference on Email and AntiSpam, Mountain View, California (2007)
Settles, B.: Active Learning. Morgan & Claypool Publishers, San Rafael (2012)
Stone, M.: Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. 36(1), 111–147 (1974)
Tong, S., Koller, D.: Support vector machine active learning with application to text classification. J. Mach. Learn. Res. 2, 45–66 (2001)
Wu, X., Kumar, V.: The Top 10 Algorithms in Data Mining. Chapman & Hall, Boca Raton (2009)
Yang, Z., Tang, J., Zhang, Y.: Active learning for streaming networked data. In: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, CIKM ’14, pp. 1129–1138. ACM, New York (2014)
Acknowledgments
This work was funded via the project ‘Improving the usability of machine learning in industrial inspection systems’ (useML) by the Austrian Research Promotion Agency (FFG) under the scope of the ‘Information and communication technology of the future’ program. This program is promoted by the Austrian Federal Ministry of Transport, Innovation and Technology (BMVIT) and the Federal Ministry of Science, Research and Economy (BMWFW).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Weigl, E., Heidl, W., Lughofer, E. et al. On improving performance of surface inspection systems by online active learning and flexible classifier updates. Machine Vision and Applications 27, 103–127 (2016). https://doi.org/10.1007/s00138-015-0731-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-015-0731-9