Tile Classification Using the CIELAB Color Model
An image processing algorithm was developed for tile shade classification on the basis of quantitative measurements in CIELAB color space. A total of 50 tile images of 10 types were recorded, and evaluated with the proposed algorithm in comparison with the conventional classification method. The objectivity of the method is based on the fact that it is not subject to inter- and intra-observer variability arising from human’s profile of competency in interpreting subjective and non-quantifiable descriptions.
Unable to display preview. Download preview PDF.
- 1.Lebrun, V.: Quality control of ceramic tiles by machine vision. Flaw Master 3000, Surface Inspection Ltd. (2001)Google Scholar
- 2.Boukouvalas, C., De Natale, F., De Toni, G., Kittler, J., Marik, R., Mirmehdi, M., Petrou, M., Le Roy, P., Salgari, R., Vernazza, G.: An Integrated System for Quality Inspection of Tiles. In: Int. Conference on Quality Control by Artificial Vision, QCAV 1997, France, pp. 49–54 (1997)Google Scholar
- 3.Deviren, M., Koray Balci, M., Murat Leloglu, U., Severcan, M.: A Feature Extraction Method for Marble Classification. In: Third International Conference on Computer Vision, Pattern Recognition & Image Processing (CVPRIP 2000), Atlantic City, pp. 25–28 (2000) (HSI)Google Scholar
- 5.Fairchild, M.D.: Color Appearance Models. Addison-Wesley, Reading (1998)Google Scholar
- 7.Coulthard, M.: Tile shade classification strategies for maximum profit. Tile & Brick international journal 16(3) (June 2000)Google Scholar