This article shows one of the applications of computer vision methods in the problem of assessing the quality of the production of ceramic bricks. The tasks of quality assessment include the selection of chips, cracks, scratches, as well as colour changes. The article provides a method of colour difference for assessing the quality of industrial products. Real images of the production process are taken as a basis, for which methods for highlighting bricks have been developed, and for each an assessment of the colour difference from the sample is carried out. The proposed solution to the problem allows you to automate and speed up the process of assessing the quality of brick products in contrast to typical schemes for solving the same problem using visual observation. 1. Shapiro, L., Stockman, J. Computer vision / Moscow: BINOM. Knowledge Laboratory, 2006, 752 p.
2. Evans, R.M. Introduction to colour theory / Moscow: Mir Publishing House, 1964, 442 p.
3. Strategy for the development of the construction industry and housing and communal services of the Russian Federation until 2030 with a forecast for the period up to 2035 / Moscow: Ministry of Construction of the Russian Federation, 2019, 82 p.
4. GOST 530–2012. Brick and ceramic stone. General specifications / Moscow: VNIISTROM “Scientific Centre of Ceramics”, 2013, 49 p.
5. Pratt, W. Digital Image Processing / Moscow: Mir, 1982, Vol. 1–2, 1104 p.
6. Vizilter, Yu.V., Zheltov, S. Yu., Bondarenko, A.V., Ososkov, M.V., Morgin, A.V. Processing and analysis of images in machine vision problems / Moscow: Fizmatkniga, 2010, 672 p.
7. GOST 13088–67, Colorimetry. Terms, letter designations/ Moscow: Committee of standards, measures and measuring instruments under the Council of Ministers of the USSR, 1990, 15 p.
8. Kataev, M. Yu., Karpov, R.K., Laminsky, K.A. Software system for detecting defects in bricks based on computer vision methods // Doklady TUSUR, 2021, V. 24, # 1, pp. 62–67.
9. Penumuru, D.P., Muthuswamy, S., Karumbu, P. Identification and classification of materials using machine vision and machine learning in the context of industry // J. Intell. Manuf. 2020, Vol. 31, pp. 1229–1241.
10. Kataev, M. Yu., Dadonova, M.M. Method of Vegetation Detection Using RGB Images Made by Unmanned Aerial Vehicles on the Basis of Colour and Texture Analysis // Light & Engineering Journal, 2019, Vol. 27, # 5, pp. 55–66.
11. Tominaga, S. Multichannel vision system for estimating surface and illumination functions // J. Opt. Soc. Am. A. 1996, Vol. 13, # 11, pp. 2163–2173.
12. Heikkinen, V., Jetsu, T., Parkkinen, J., Hauta-Kasari, M., Jaaskelainen, T., Lee, S. Regularized learning framework in the estimation of reflectance spectra from camera responses // J. Opt. Soc. Am. A. 2007, Vol.. 24, pp. 2673–2683.
13. Tapia, C., A.S. de Miguel, Zamorano, J. LICAUCM lamps spectral database / UCM e-Prints, 2017, 28 p.
14. Bassiou, N., Kotropoulos, C. Colour image histogram equalization by absolute discounting backoff // Computer Vision and Image Understanding, 2007, Vol. 107, pp. 108–122.
15. GOST 379–2015 Brick, stones, blocks and silicate partition slabs. General specifications / Moscow: Standartinform, 2015, 22 p.
16. Miao, R.H., Tang, J.L., Chen, X.Q. Classification of farmland images based on colour features // J. Vis. Commun. Image Represent, 2015, Vol. 29, pp. 138–146.

• Previous article
• Next article

• image
• computer vision
• pattern
• comparison
• histogram
• production output