Textural features based on run length encoding in the classification of furniture surfaces with the orange skin defect

Main Article Content

Jakub Pach
Izabella Antoniuk
Leszek Chmielewski
Jarosław Górski
Michał Kruk
Jarosław Kurek
Arkadiusz Orłowski
Katarzyna Śmietańska
Bartosz Świderski
Grzegorz Wieczorek

Keywords : quality inspection, furniture surface, orange skin, textural features, run length coding, thresholded image, one nearest neighbour, leave-one-out testing

Textural features based upon thresholding and run length encoding have been successfully applied to the problem of classification of the quality of lacquered surfaces in furniture exhibiting the surface defect known as orange skin. The set of features for one surface patch consists of 12 real numbers. The classifier used was the one nearest neighbour classifier without feature selection. The classification quality was tested on 808 images 300 by 300 pixels, made under controlled, close-to-tangential lighting, with three classes: good, acceptable and bad, in close to balanced numbers. The classification accuracy was not smaller than 98% when the tested surface was not rotated with respect to the training samples, 97% for rotations up to 20 degrees and 95.5% in the worst case for arbitrary rotations.

Article Details

How to Cite
Pach, J., Antoniuk, I., Chmielewski, L., Górski, J., Kruk, M., Kurek, J., Orłowski, A., Śmietańska, K., Świderski, B., & Wieczorek, G. (2019). Textural features based on run length encoding in the classification of furniture surfaces with the orange skin defect. Machine Graphics and Vision, 28(1/4), 35–45. https://doi.org/10.22630/MGV.2019.28.1.4

M. Allard, C. Jaecques, and I. Kauffer. Coating material which can be thermally cured and hardened by actinic radiation and use thereof, September 27 2005. US Patent 6,949,591.

L. Armesto, J. Tornero, A. Herraez, and J. Asensio. Inspection system based on artificial vision for paint defects detection on cars bodies. In 2011 IEEE International Conference on Robotics and Automation, pages 1–4, May 2011. https://doi.org/10.1109/ICRA.2011.5980570. (Crossref)

V. Bucur. Techniques for high resolution imaging of wood structure: a review. Measurement Science and Technology, 14(12):R91, 2003. https://doi.org/10.1088/0957-0233/14/12/R01. (Crossref)

G. C. Cawley and N. L. C. Talbot. Efficient leave-one-out cross-validation of kernel Fisher discriminant classifiers. Pattern Recognition, 36(11):2585 – 2592, 2003. https://doi.org/10.1016/S0031-3203(03)00136-5. (Crossref)

L. J. Chmielewski, K. Laszewicz-Śmietańska, P. Mitas, A. Orłowski, et al. Defect detection in furniture elements with the Hough transform applied to 3D data. In R. Burduk et al., editors, Proc. 9th Int. Conf. Computer Recognition Systems CORES 2015, volume 403 of Advances in Intelligent Systems and Computing, pages 631–640, Wrocław, Poland, 25-27 May 2015. Springer. https://doi.org/10.1007/978-3-319-26227-7 59. (Crossref)

L. J. Chmielewski, A. Orłowski, K. Śmietańska, J. Górski, et al. Detection of surface defects of type

‘orange skin’ in furniture elements with conventional image processing methods. In F. Huang and A. Sugimoto, editors, Image and Video Technology – PSIVT 2015 Workshops, volume 9555 of Lecture Notes in Computer Science, pages 26–37, Auckland, New Zealand, 23-27 Nov 2015. Springer, 2016. https://doi.org/10.1007/978-3-319-30285-0_3. (Crossref)

L. J. Chmielewski, A. Orłowski, G. Wieczorek, K. Śmietańska, and J. Górski. Testing the limits of detection of the ‘orange skin’ defect in furniture elements with the HOG features. In N.T. Nguyen, S. Tojo, et al., editors, Proc. 9th Asian Conference on Intelligent Information and Database Systems ACIIDS 2017, Part II, volume 10192 of Lecture Notes in Artificial Intelligence, pages 276–286, Kanazawa, Japan, 3-5 Apr 2017. Springer. https://doi.org/10.1007/978-3-319-54430-4_27. (Crossref)

A. Jóżwik, S. Serpico, and F. Roli. A parallel network of modified 1-NN and k-NN classifiers – Application to remote-sensing image classification. Pattern Recogn. Lett., 19(1):57–62, January 1998. https://doi.org/10.1016/S0167-8655(97)00155-4. (Crossref)

D. A. Karras. Improved defect detection using support vector machines and wavelet feature extraction based on vector quantization and SVD techniques. In Proc. Int. Joint Conf. on Neural Networks, 2003, volume 3, pages 2322–2327, July 2003. https://doi.org/10.1109/IJCNN.2003.1223774. (Crossref)

J. Konieczny and G. Meyer. Computer rendering and visual detection of orange peel. Journal of Coatings Technology and Research, 9(3):297–307, 2012. https://doi.org/10.1007/s11998-011-9378-2. (Crossref)

M. Kruk, B. Świderski, K. Śmietańska, J. Kurek, L. J. Chmielewski, J. Górski, and A. Orłowski. Detection of ‘orange skin’ type surface defects in furniture elements with the use of textural features. In K. Saeed, W. Homenda, and R. Chaki, editors, Proc. 16th IFIP TC8 Int. Conf. Computer Information Systems and Industrial Management Applications CISIM 2017, volume 10244 of Lecture Notes in Computer Science, pages 402–411, Białystok, Poland, 16-18 Jun 2017. Springer, Cham. https://doi.org/10.1007/978-3-319-59105-6 34. (Crossref)

W. J. Krzanowski and D. J. Hand. Assessing error rate estimators: The leave-one-out method reconsidered. Australian Journal of Statistics, 39(1):35–46, 1997. https://doi.org/10.1111/j.1467-842X.1997.tb00521.x. (Crossref)

K. Laszewicz and J. Górski. Control charts as a tool for the management of dimensional accuracy of mechanical wood processing (in Russian). Annals of Warsaw University of Life Sciences-SGGW, Forestry and Wood Technology, 65:88–92, 2008.

K. Laszewicz, J. Górski, and J. Wilkowski. Long-term accuracy of MDF milling process–development of adaptive control system corresponding to progression of tool wear. European Journal of Wood and Wood Products, 71(3):383–385, 2013. https://doi.org/10.1007/s00107-013-0679-2. (Crossref)

K. Laszewicz, J. Górski, J. Wilkowski, and P. Czarniak. Analysis of dimensional accuracy of milling process. Wood Research, 58(3):451–463, 2013.

F. Longuetaud, F. Mothe, B. Kerautret, et al. Automatic knot detection and measurements from X-ray CT images of wood: A review and validation of an improved algorithm on softwood samples. Computers and Electronics in Agriculture, 85(0):77–89, 2012. https://doi.org/10.1016/j.compag.2012.03.013. (Crossref)

E.-C. Musat, E.-A. Salca, F. Dinulica, et al. Evaluation of color variability of oak veneers for sorting. BioResources, 11(1):573–584, 2016. https://doi.org/10.15376/biores.11.1.573-584. (Crossref)

M. Otsu. A threshold selection method from gray-level histograms. IEEE Trans. Systems, Man and Cybern., 9(1):62–66, 1979. https://doi.org/10.1109/TSMC.1979.4310076. (Crossref)

J. L. Pach. Identification of the author of Latin manuscripts with the use of image processing methods. Ph.d. thesis, Warsaw University of Technology, Faculty of Electronics and Information Technology, Warsaw, 2019.

M. Sezgin and B. Sankur. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, 13(1):146–165, 2004. https://doi.org/10.1117/1.1631315. (Crossref)

B. Świderski, M. Kruk, G. Wieczorek, J. Kurek, K. Śmietańska, L. J. Chmielewski, J. Górski, and A. Orłowski. Feature selection for ‘orange skin’ type surface defect in furniture elements. In L. Rutkowski et al., editors, Proc. Int. Conf. on Artificial Intelligence and Soft Computing ICAISC 2018, volume 10842 of Lecture Notes in Artificial Intelligence, pages 81–91, Zakopane, Poland, 3-7 Jun 2018. https://doi.org/10.1007/978-3-319-91262-2_8. (Crossref)



Download data is not yet available.
Recommend Articles
Most read articles by the same author(s)
1 2 > >>