Color-Texture Image Analysis for Automatic Failure Detection in Tiles
- 905 Downloads
The defects in tiles are directly related with changes in the structure or color components producing spots or stains in the final product. Usually, a visual inspection is carried out in order to detect one of such common defects in tiles; however this process depends on the expertise and abilities of the operator on duty. In this paper, we present the automation of defect detection in tiles using vision algorithms and Artificial Neural Networks (ANN). Color and texture information extracted from real tile images are used as input to a classifier based on neural networks. Setting parameters for extracting the texture attributes are obtained performing detailed tests of different distances, orientations and window sizes. An initial architecture of the ANN is obtained using texture features extracted from Brodatz images. Next, the neural network parameters are computed using real images from the tile database. The experimental tests validate the global performance, accuracy and feasibility of our approach.
KeywordsColor-texture attributes CIELab color space Tile failure classification Artificial Neural Networks (ANN)
- 2.Hocenski, Z., Keser, T.: Failure detection and isolation in ceramic tile edges based on contour descriptor analysis. In: Mediterranean Conference on Control Automation, MED 2007, pp. 1–6 (2007). doi: 10.1109/MED.2007.4433713.
- 4.Boukouvalas, C., Kittler, J., Marik, R., Petrou, M.: Automatic grading of ceramic tiles using machine vision. In: 1994 IEEE International Symposium on Industrial Electronics, Symposium Proceedings, ISIE 1994, pp. 13–18 (1994). doi: 10.1109/ISIE.1994.333123.
- 5.Boukouvalas, C., Kittler, J., Marik, R., Mirmehdi, M., Petrou, M.: Ceramic tile inspection for colour and structural defects. In: Proceedings of AMPT95, pp. 390–399 (1995)Google Scholar
- 7.Aborisade, D.O., Ibiyemi, T.S.: Ceramic Wall Tile Quality Classification Training Algorithms Using Statistical Approach. Research Journal of Applied Sciences 2, 1255–1260 (2007). http://medwelljournals.com/abstract/?doi=rjasci.2007.1255.1260
- 10.Smith, M.L., Stamp, R.J.: Automated inspection of textured ceramic tiles. Comput. Ind. 43, 73–82 (2000). doi: 10.1016/S0166-3615(00)00052-X, Elsevier
- 11.Rimac-drlje, S., Keller, A., Nyarko, K.E.: Self-learning system for surface failure detection. In: 13th European Signal Processing Conference, pp. 1–4 (2005)Google Scholar