Segmentation of Fabric Defect Images Based on PCNN Model and Symmetric Tsallis Cross Entropy

Abstract:

Segmentation of defect images is an important step in the automatic fabric defect detection. In order to extract fabric defects effectively, a segmentation method of fabric defect images based on pulse coupled neural network (PCNN) model and symmetric Tsallis cross entropy is proposed. The image is segmented by PCNN according to the gray strength difference between fabric defect area and non-defect area. To guarantee that the grayscale inside the object and background is uniform after segmentation, symmetric Tsallis cross entropy is used as the image segmentation criterion to select the optimal threshold and iteration number. A large number of experimental results show that, compared with the related segmentation methods such as Otsu method, PCNN method, the method based on PCNN and cross entropy, the segmentation effect of the proposed method is the best. The texture of non-defect area is removed more completely, and the defect area is segmented more accurately.

• Periodical: Advanced Materials Research (Volumes 760-762)
• Pages: 1472-1476
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.760-762.1472
• Online since: September 2013
• Authors: Hong Wan, Yi Quan Wu, Zhao Qing Cao, Zhi Long Ye
• Keywords: Fabric Defect Detection, Image Segmentation, Pulse Coupled Neural Network, Symmetric Tsallis Cross Entropy

References

[1] A. Kumar, Computer-vision-based fabric defect detection: a survey, IEEE Transactions on Industrial Electronics, vol. 55, no. 1, pp.348-363, (2008).

DOI: 10.1109/tie.1930.896476

[2] S.W. Zhu, Fabric defects segmentation approach based on texture primitive, 2007 International Conference on Machine Learning and Cybernetics, Hong Kong, vol. 3, pp.1596-1600, (2007).

DOI: 10.1109/icmlc.2007.4370400

[3] G. Huang, J. Li, and J.G. Pan. A fast 2D Otsu image segmentation algorithm based on particle swam optimization algorithm, Journal of Image and Graphics, vol. 16, no. 3, pp.377-381, 2011. (in Chinese).

[4] Q. Chen, L. Zhao, J. Lu, G. Kuang, N. Wang, and Y. Jiang, Modified two-dimensional Otsu image segmentation algorithm and fast realization, IET Image Processing, vol. 6, no. 4, pp.426-433, (2012).

DOI: 10.1049/iet-ipr.2010.0078

[5] C.H. Chan, and G. Pang, Fabric defect detection by Fourier analysis, IEEE Transactions on Industry Application, vol. 36, no. 5, pp.1267-1277, (2000).

DOI: 10.1109/28.871274

[6] S.W. Zhu, and C.Y. Hao, An approach for fabric defect image segmentation based on the improved convertional PCNN model, Acta Electronica Sinaca, vol. 40, no. 3, pp.611-616, 2012. (in Chinese).

[7] Q. Liu, Y.D. Ma, and Z.B. Qian, Automated image segmentation using improved PCNN model based on cross-entrepy, Journal of Image and Graphics, vol. 10, no. 5, pp.581-584, 2005. (in Chinese).

[8] Y.Q. Wu, Y. Shen, T. Gang, Y. Ji and S.F. Fen, Thresholding for small target image based on 2-D symmetric Tsallis cross entropy, Chinese Journal of Scientific Instrument, vol. 32, no. 10, pp.2161-2167, 2011. (in Chinese).