Recognizing steel elements with BRDF and k-nearest neighbors

• Autorzy: Ciszkiewicz Adam , Jaglarz Janusz , Uhl Tadeusz

Identyfikatory

DOI

10.24425/mms.2023.147958

• Języki publikacji: EN

Abstrakty

EN

The paper deals with analysis of recognition of surface quality with reflective structures. Such surfaces are common in metallic materials cut using a saw or polished. There are no easy methods to identify such elements after machining. This issue is crucial in the industry for quality control as recognition of the elements, for instance after failure, allows for a detailed study of their manufacturing process. Firstly, six cuboid steel elements were obtained from a larger beam with a circular saw. Then, the bidirectional reflection distribution function (BRDF) was obtained for each element 3 times. The BRDF profiles were used in custom recognition software based on the K-nearest neighbors algorithm. In total, 140 variants of the classifier were tested and analyzed. Additionally, each variant was solved 200 times with different splits of the dataset. The results showed a high multiclass accuracy in all considered variants of the algorithm, with multiple variants achieving 100% accuracy. This level of performance was attained with only 1 to 2 training samples per class. Its low numerical complexity, easy experimental procedure, and “one-shot” nature allow for fast recognition, which is crucial in industrial applications.

Słowa kluczowe

EN

metallic surface; reflective surface; bidirectional reflection distribution function; classification

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2023
• Tom: Vol. 30, nr 4
• Strony: 721--736
• Opis fizyczny: Bibliogr. 49 poz., rys., tab., wykr., wzory

Twórcy

autor

Ciszkiewicz Adam

• Faculty of Mechanical Engineering, Cracow University of Technology, Al. Jana Pawła II 37, 31-864 Cracow, Poland

autor

Jaglarz Janusz

• Faculty of Material Engineering, Cracow University of Technology, Al. Jana Pawła II 37, 31-864 Cracow, Poland

autor

Uhl Tadeusz

• Department of Robotics and Mechatronics, Faculty of Mechanical Engineering and Robotics, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059, Cracow, Poland

Bibliografia

• [1] Nicodemus, F. E. (1965). Reflectance Nomenclature and Directional Reflectance and Emissivity. Applied Optics, 4(7), 767-775. https://doi.org/10.1364/ao.9.001474
• [2] Asmail, C. (1991). Bidirectional scattering distribution function (BSDF): A systematized bibliography. Journal of Research of the National Institute of Standards and Technology, 96(2), 215-223. https://doi.org/10.6028/jres.096.010
• [3] Neogi, N., Mohanta, D. K., & Dutta, P. K. (2014). Review of vision-based steel surface inspection systems. EURASIP Journal on Image and Video Processing, 50. https://doi.org/10.1186/1687-5281-2014-50
• [4] Mikeš, S., & Haindl, M. (2019). View Dependent Surface Material Recognition. Bebis G. et al. (Eds) Advances in Visual Computing. ISVC 2019. Lecture Notes in Computer Science, 11844. Springer, Cham.
• [5] Hahlweg, C., & Rothe, H. (2005). Classification of optical surface properties and material recognition using multi-spectral BRDF data measured with a semi-hemispherical spectro-radiometer in VIS and NIR. Proc. SPIE 5965, Optical Fabrication, Testing, and Metrology II, 59650G. https://doi.org/10.1117/12.624838
• [6] Stover, J. C. (1995). Optical Scattering: Measurement and Analysis (2nd. ed.). SPIE Press. https://doi.org/9780819478443
• [7] Gong, R., Wu, C., & Chu, M. (2018). Steel surface defect classification using multiple hyper-spheres support vector machine with additional information. Chemometrics and Intelligent Laboratory Systems, 172 (December 2017), 109-117. https://doi.org/10.1016/j.chemolab.2017.11.018
• [8] Chu, M., Gong, R., Gao, S., & Zhao, J. (2017). Steel surface defects recognition based on multi-type statistical features and enhanced twin support vector machine. Chemometrics and Intelligent Laboratory Systems, 171 (August), 140-150. https://doi.org/10.1016/j.chemolab.2017.10.020
• [9] Zheng, X., Wang, H., Chen, J., Kong, Y., & Zheng, S. (2020). A Generic Semi-Supervised Deep Learning-Based Approach for Automated Surface Inspection. IEEE Access, 8, 114088-114099. https://doi.org/10.1109/ACCESS.2020.3003588
• [10] Rakels, J. H. (1989). Recognised Surface Finish Parameters Obtained from Diffraction Patterns of Rough Surfaces. Proc. SPIE 1009, Surface Measurement and Characterization.
• [11] Kumar, H., Ramkumar, J., & Venkatesh, K. S. (2018). Surface texture evaluation using 3D reconstruction from images by parametric anisotropic BRDF. Measurement: Journal of the International Measurement Confederation, 125 (April), 612-633. https://doi.org/10.1016/j.measurement.2018.04.090
• [12] Ngan, A., Durand, F., & Matusik, W. (2005). Experimental Analysis of BRDF Models. Mitsubishi Electric Research Laboratories
• [13] Ghosh, A., Achutha, S., Heidrich, W., & O’Toole, M. (2007). BRDF acquisition with basis illumination. 2007 IEEE 11th International Conference on Computer Vision (pp. 1-8). IEEE. https://doi.org/10.1109/ICCV.2007.4408935
• [14] Dana, K. J. (2001). BRDF/BTF Measurement Device. Proceedings Eighth IEEE International Conference on Computer Vision, ICCV 2001 (Vol. 2, pp. 460-466). IEEE. https://doi.org/10.1109/ICCV.2001.937661
• [15] Lai, Q., Liu, B., Zhao, J., Zhao, Z., & Tan, J. (2020). BRDF characteristics of different textured fabrics in visible and near-infrared band. Optics Express, 28(3), 3561. https://doi.org/10.1364/oe.385135
• [16] Liu, Y., Xu, K., & Xu, J. (2019). An improved MB-LBP defect recognition approach for the surface of steel plates. Applied Sciences (Switzerland), 9(20). https://doi.org/10.3390/app9204222
• [17] Zhang, D., Song, K., Xu, J., He, Y., & Yan, Y. (2020). Unified detection method of aluminium profile surface defects: Common and rare defect categories. Optics and Lasers in Engineering, 126 (August 2019). https://doi.org/10.1016/j.optlaseng.2019.105936
• [18] Acharya, A. K., Sahu, P. K., & Jena, S. R. (2019). Deep neural network based approach for detection of defective solar cell. Materials Today: Proceedings, 39, 2009-2014. https://doi.org/10.1016/j.matpr.2020.09.048
• [19] Gao, Y., Gao, L., Li, X., & Yan, X. (2020). A semi-supervised convolutional neural network-based method for steel surface defect recognition. Robotics and Computer-Integrated Manufacturing, 61 (May 2019). https://doi.org/10.1016/j.rcim.2019.101825
• [20] Chen, W., Gao, Y., Gao, L., & Li, X. (2018). A New Ensemble Approach based on Deep Convolutional Neural Networks for Steel Surface Defect classification. Procedia CIRP, 72, 1069-1072. https://doi.org/10.1016/j.procir.2018.03.264
• [21] Fu, G., Sun, P., Zhu, W., Yang, J., Cao, Y., Yang, M. Y., & Cao, Y. (2019). A deep-learning-based approach for fast and robust steel surface defects classification. Optics and Lasers in Engineering, 121 (February), 397-405. https://doi.org/10.1016/j.optlaseng.2019.05.005
• [22] Kou, X., Liu, S., Cheng, K., & Qian, Y. (2021). Development of a YOLO-V3-based model for detecting defects on steel strip surface. Measurement, 109454. https://doi.org/10.1016/j.measurement.2021.109454
• [23] He, X., Wang, T., Wu, K., & Liu, H. (2021). Automatic defects detection and classification of low carbon steel WAAM products using improved remanence/magneto-optical imaging and cost-sensitive convolutional neural network. Measurement, 173 (August 2020), 108633. https://doi.org/10.1016/j.measurement.2020.108633
• [24] He, D., Xu, K., & Zhou, P. (2019). Defect detection of hot rolled steels with a new object detection framework called classification priority network. Computers and Industrial Engineering, 128 (December 2018), 290-297. https://doi.org/10.1016/j.cie.2018.12.043
• [25] Kim, M. S., Park, T., & Park, P. (2019). Classification of Steel Surface Defect Using Convolutional Neural Network with Few Images. 2019 12th Asian Control Conference, ASCC 2019 (pp. 1398-1401).
• [26] Deshpande, A. M., Minai, A. A., & Kumar, M. (2020). One-shot recognition of manufacturing defects in steel surfaces. Procedia Manufacturing, 48, 1064-1071. https://doi.org/10.1016/j.promfg.2020.05.146
• [27] Schlagenhauf, T., Yildirim, F., Brückner, B., & Fleischer, J. (2020). Siamese basis function networks for defect classification. ArXiv.
• [28] Di, H., Ke, X., Peng, Z., & Dongdong, Z. (2019). Surface defect classification of steels with a new semi-supervised learning method. Optics and Lasers in Engineering, 117 (February), 40-48. https://doi.org/10.1016/j.optlaseng.2019.01.011
• [29] He, Y., Song, K., Dong, H., & Yan, Y. (2019). Semi-supervised defect classification of steel surface based on multi-training and generative adversarial network. Optics and Lasers in Engineering, 122(May), 294-302. https://doi.org/10.1016/j.optlaseng.2019.06.020
• [30] Nguyen, V. H., Pham, V. H., Cui, X., Ma, M., & Kim, H. (2017). Design and evaluation of features and classifiers for OLED panel defect recognition in machine vision. Journal of Information and Telecommunication, 1(4), 334-350. https://doi.org/10.1080/24751839.2017.1355717
• [31] Gupta, S., Sarkar, J., Kundu, M., Bandyopadhyay, N. R., & Ganguly, S. (2020). Automatic recognition of SEM microstructure and phases of steel using LBP and random decision forest operator. Measurement, 151, 107224. https://doi.org/10.1016/j.measurement.2019.107224
• [32] Ciocan, R., Petulescu, P., Ciobanu, D., & Roth, D. J. (2000). Use of the neural networks in the recognition of the austenitic steel types. NDT and E International, 33(2), 85-89. https://doi.org/10.1016/S0963-8695(99)00032-8
• [33] Arenas, M. P., Rocha, T. J., Angani, C. S., Ribeiro, A. L., Ramos, H. G., Eckstein, C. B., Rebello, J. M. A., & Pereira, G. R. (2018). Novel austenitic steel ageing classification method using eddy current testing and a support vector machine. Measurement, 127 (September 2017), 98-103. https://doi.org/10.1016/j.measurement.2018.05.101
• [34] Zhang, T., Xia, D., Tang, H., Yang, X., & Li, H. (2016). Classification of steel samples by laser-induced breakdown spectroscopy and random forest. Chemometrics and Intelligent Laboratory Systems, 157, 196-201. https://doi.org/10.1016/j.chemolab.2016.07.001
• [35] Khudhair, S., Taher, M. K., & Mohammed, M. (2021). Strain rate effect on mechanical properties of 0.24% carbon steel using artificial neural network. Materials Today: Proceedings, https://doi.org/10.1016/j.matpr.2021.03.514
• [36] Shiradkar, R., Shen, L., Landon, G., Ong, S. H., & Tan, P. (2014). A new perspective on material classification and ink identification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 2275-2282). https://doi.org/10.1109/CVPR.2014.291
• [37] Liu, C., Yang, G., & Gu, J. (2013). Learning discriminative illumination and filters for raw material classification with optimal projections of bidirectional texture functions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 1430-1437). https://doi.org/10.1109/CVPR.2013.188
• [38] Liu, C., & Gu, J. (2014). Discriminative illumination: Per-pixel classification of raw materials based on optimal projections of spectral BRDF. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(1), 86-98. https://doi.org/10.1109/TPAMI.2013.110
• [39] Jehle, M., Sommer, C., & Jähne, B. (2010). Learning of optimal illumination for material classification. Lecture Notes in Computer Science, 6376 LNCS (September), 563-572. https://doi.org/10.1007/978-3-642-15986-2_57
• [40] Altman, N. S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. American Statistician, 46(3), 175-185. https://doi.org/10.1080/00031305.1992.10475879
• [41] Marszałek, K., Wolska, N., & Jaglarz, J. (2015). Angle resolved scattering combined with optical profilometry as tools in thin films and surface survey. Acta Physica Polonica A, 128(1), 81-86. https://doi.org/10.12693/APhysPolA.128.81
• [42] Mocanu, D. C., & Mocanu, E. (2018). One-shot learning using mixture of variational autoencoders: A generalization learning approach. ArXiv, April.
• [43] Varmuza, K., Filzmoser, P., Hilchenbach, M., Krüger, H., & Silén, J. (2014). KNN classification - evaluated by repeated double cross validation: Recognition of minerals relevant for comet dust. Chemometrics and Intelligent Laboratory Systems, 138, 64-71. https://doi.org/10.1016/j.chemolab.2014.07.011
• [44] Chen, L., Wang, C., Chen, J., Xiang, Z., & Hu, X. (2020). Voice Disorder Identification by using Hilbert-Huang Transform (HHT) and K Nearest Neighbor (KNN). Journal of Voice. https://doi.org/10.1016/j.jvoice.2020.03.009
• [45] Elgamel, M. S., & Dandoush, A. (2015). A modified Manhattan distance with application for localization algorithms in ad-hoc WSNs. Ad Hoc Networks, 33, 168-189. https://doi.org/10.1016/j.adhoc.2015.05.003
• [46] Peiravi, A., & Kheibari, H. T. (2008). A fast algorithm for connectivity graph approximation using modified Manhattan distance in dynamic networks. Applied Mathematics and Computation, 201(1-2), 319-332. https://doi.org/10.1016/j.amc.2007.12.026
• [47] Savitzky, A., & Golay, M. J. E. (1964). Smoothing and Differentiation of Data by Simplified Least Squares Procedures. Analytical Chemistry. 36(8): 1627-1639.
• [48] Schmid, M., Rath, D., & Diebold, U. (2022). Why and How Savitzky-Golay Filters Should Be Replaced. ACS Measurement Science Au, 2(2), 185-196.
• [49] van der Walt, S., Colbert, S. C., & Varoquaux, G. (2011). The NumPy Array: A Structure for Efficient Numerical Computation. Computing in Science & Engineering, 13(2), 22-30. https://doi.org/10.1109/MCSE.2011.37