• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Block Sparse Low-rank Matrix Decomposition based Visual Defect Inspection of Rail Track Surfaces

Vol. 13, No. 12, December 31, 2019
10.3837/tiis.2019.12.014, Download Paper (Free):

Abstract

Low-rank matrix decomposition has shown its capability in many applications such as image in-painting, de-noising, background reconstruction and defect detection etc. In this paper, we consider the texture background of rail track images and the sparse foreground of the defects to construct a low-rank matrix decomposition model with block sparsity for defect inspection of rail tracks, which jointly minimizes the nuclear norm and the 2-1 norm. Similar to ADM, an alternative method is proposed in this study to solve the optimization problem. After image decomposition, the defect areas in the resulting low-rank image will form dark stripes that horizontally cross the entire image, indicating the preciselocations of the defects. Finally, a two-stage defect extraction method is proposed to locate the defect areas. The experimental results of the two datasets show that our algorithm achieved better performance compared with other methods.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
L. Zhang, S. Chen, Y. Cen, Y. Cen, H. Wang and M. Zeng, "Block Sparse Low-rank Matrix Decomposition based Visual Defect Inspection of Rail Track Surfaces," KSII Transactions on Internet and Information Systems, vol. 13, no. 12, pp. 6043-6062, 2019. DOI: 10.3837/tiis.2019.12.014.

[ACM Style]
Linna Zhang, Shiming Chen, Yigang Cen, Yi Cen, Hengyou Wang, and Ming Zeng. 2019. Block Sparse Low-rank Matrix Decomposition based Visual Defect Inspection of Rail Track Surfaces. KSII Transactions on Internet and Information Systems, 13, 12, (2019), 6043-6062. DOI: 10.3837/tiis.2019.12.014.