A sparse representation method for image-based surface defect detection

Abstract

In this paper, an efficient sparse representation-based method is presented for detecting surface defects. The proposed method uses the sparse degree of coefficient in the redundant dictionary for checking whether the test image is defective or not, and the binary representation of the defective images is obtained, according to the global coefficient feature. Owing to the requirements for the efficiency and detecting quality, the block proximal gradient operator is introduced to speed up the online dictionary learning. Considering the correlation among the testing samples, prior knowledge is applied in the orthogonal-matching-pursuit sparse representation algorithm to improve the speed of sparse coding. Experimental results demonstrate that the proposed detection method can effectively detect and extract the defects of the surface images, and has broad applicability.

References

[1] ZhangZ., XuY., YangJ., LiX., ZhangD.. IEEE Access, 2015, 3: 490

[2] OlshausenB. A., FieldD. J.. Nature, 1996, 381: 607

[3] EnganK., AaseS. O., HusoyJ. H.. Method of optimal directions for frame design, IEEE International Conference on Acoustics, Speech, and Signal Processing, 1999, 5: 2443

[4] EnganK., SkrettingK., HusøyJ. H.. Digital Signal Processing, 2007, 17: 32

[5] PtuchacR., SavakisA. E.. IEEE Transactions on Image Processing, 2014, 23: 1737

[6] AharonM., EladM., BrucksteinA.. IEEE Transactions on Signal Processing, 2006, 54: 4311

[7] YangJ., ZhangX., PengW., LiuZ.. Multimedia Tools and Applications, 2016, 75: 13107

[8] LiY., LiF., BaiB., ShenQ.. Applied Optics, 2016, 55: 1814

[9] MairalJ., BachF., PonceJ., SapiroG., ZissermanA.. Non–local Sparse Models for Image Restoration, IEEE 12th International Conference on Computer Vision, 2272, 2009,

[10] XuY., YinW.. SIAM Journal on Imaging Sciences, 2013, 6: 1758

[11] TroppJ. A., GilbertA. C.. IEEE Transactions on Information Theory, 2008, 53: 4655

[12] LiG., VarshneyP. K.. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7: 4937

[13] MallatS. G., ZhangZ.. IEEE Transactions on Signal Processing, 1993, 41: 3397

[14] WANGJ., WANGG., LIL.. IEICE Transactions on Information and Systems, 2017, 100: 3032

[15] XuD., DuL., LiuH., WangP., YanJ., CongY., HanX.. IEEE Transactions Signal Processing, 2015, 63: 3076