基于离散余弦变换过完备字典的机织物纹理稀疏表征

doi:10.13475/j.fzxb.20170404407

摘要/Abstract

摘要：

为进一步研究基于字典学习的机织物纹理表征算法的稳定性与可比性，提出用离散余弦变换（DCT）过完备字典稀疏表征算法来重构织物纹理图像。重点探讨了稀疏度、子窗口大小、字典个数对纹理表征效果的影响，利用均方根误差和峰值信噪比指标对机织物原图与重构图像之间的近似程度进行量化，并确定最终优选的稀疏度为10，子窗口大小为8像素×8像素，字典个数为256。实验结果表明，所提方法不仅方便快捷，还可得到较好的表征效果。此外，其DCT过完备字典峰值信噪比值仅次于基于训练的自适应学习字典，且优于主成分分析和非稀疏表征算法约4 dB。

Abstract:

In order to investigate the stationary and comparability of the algorithm for woven fabric texture representation based on dictionary learning, the sparse representation with over-complete discrete cosine transform (DCT) dictionary was used to characterize the woven fabric texture. Firstly, the influence of sparsity on woven fabric texture reconstruction was investigated. Ttwo indexes with root mean square error and peak signal to noise ratio were calculated to quantify the approximation of original image and reconstructed image. And then the final chosen sparsity value is 10, the image patch size is 8 pixel × 8 pixel, and the number of dictionary atom is 256. Experiments demonstrated that the proposed algorithm is quick, has simple calculation and can achieve rather good effect. In addition, the method not only can achieve stable results, but also its peak signal to noise ratio is better about 4dB than pincipal compinent analysis and non-sparse representation algorithm on average, which is only inferior to the K singular value decomposition learned dictionary.

Key words: woven fabric texture, discrete cosine transform over-complete dictionary, sparse representation, pincipal component analysis

吴莹汪军周建. 基于离散余弦变换过完备字典的机织物纹理稀疏表征[J]. 纺织学报, 2018, 39(01): 157-163.

参考文献 22

[1]	Wang X, Georganas ND, Petriu EM. Fabric Texture Analysis Using Computer Vision Techniques [J]. Ieee Transactions on Instrumentation and Measurement, 2011, 60(1): 44-56.
[2]	贡玉南，华建兴，黄秀宝. 纺织品表面纹理的图像分析方法 [J]. 中国纺织大学学报, 1998, 24(2): 111-4.
[3]	Liu C, Fu Y, Wu N. Novel testing equipment for fabric wrinkle resistance simulating actual wear [J]. Textile Research Journal, 2014, 84(10): 1059-69.
[4]	Lachkar A, Benslimane R, D'Orazio L, et al. Textile woven fabric recognition using Fourier image analysis techniques: Part II - texture analysis for crossed-states detection [J]. Journal of the Textile Institute, 2005, 96(3): 179-83.
[5]	Li CL, Yang RM, Liu ZF, et al. Fabric defect detection via learned dictionary-based visual saliency [J]. International Journal of Clothing Science and Technology, 2016, 28(4): 530-42.
[6]	Li PF, Zhang HH, Jing JF, et al. Fabric defect detection based on multi-scale wavelet transform and Gaussian mixture model method [J]. Journal of the Textile Institute, 2015, 106(6): 587-92.
[7]	Ngan HYT, Pang GKH, Yung NHC. Automated fabric defect detection-A review [J]. Image and Vision Computing, 2011, 29(7): 442-58.
[8]	Qu T, Zou L, Zhang QL, et al. Defect detection on the fabric with complex texture via dual-scale over-complete dictionary [J]. Journal of the Textile Institute, 2016, 107(6): 743-56.
[9]	Jian Z, Semenovich D, Sowmya A, et al. Sparse Dictionary Reconstruction for Textile Defect Detection [M]. 2012.
[10]	Mao Z, Wan X, Wang J, et al. Woven Fabric Image Reconstruction Based on Dictionary Learning [J]. Journal of Donghua University Natural Science Edition, 2016, 42(1): 35-9.
[11]	Donoho DL, Tsaig Y, Drori I, et al. Sparse Solution of Underdetermined Systems of Linear Equations by Stagewise Orthogonal Matching Pursuit [J]. Ieee Transactions on Information Theory, 2012, 58(2): 1094-121.
[12]	Temlyakov VN. Weak greedy algorithms[*]This research was supported by National Science Foundation Grant DMS 9970326 and by ONR Grant N00014‐96‐1‐1003 [J]. Advances in Computational Mathematics, 2000, 12(2): 213-27.
[13]	Chen SSB, Donoho DL, Saunders MA. Atomic decomposition by basis pursuit [J]. Siam Journal on Scientific Computing, 1998, 20(1): 33-61.
[14]	Candes EJ, Donoho DL. Continuous Curvelet Transform - I. Resolution of the wavefront set [J]. Applied and Computational Harmonic Analysis, 2005, 19(2): 162-97.
[15]	Do MN, Vetterli M. The contourlet transform: an efficient directional multiresolution image representation [J]. IEEE Transactions on Image Processing, 2005, 14(12): 2091-106.
[16]	Sch?lkopf B, Platt J, Hofmann T. Efficient sparse coding algorithms; proceedings of the Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December, F, 2006 [C].
[17]	Le Pennec E, Mallat S. Sparse geometric image representations with bandelets [J]. Ieee Transactions on Image Processing, 2005, 14(4): 423-38.
[18]	Wang YH, Shi MJ, You S, et al. DCT Inspired Feature Transform for Image Retrieval and Reconstruction [J]. Ieee Transactions on Image Processing, 2016, 25(9): 4406-20.
[19]	Engan K, Aase SO, Husoy JH. Frame based signal compression using method of optimal directions\n(MOD) [M]. 1999.
[20]	Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J]. Ieee Transactions on Signal Processing, 2006, 54(11): 4311-22.
[21]	Rubinstein R, Zibulevsky M, Elad M. Double Sparsity: Learning Sparse Dictionaries for Sparse Signal Approximation [J]. Ieee Transactions on Signal Processing, 2010, 58(3): 1553-64.
[22]	蔡红. 基于稀疏表示的SAR图像压缩方法研究 [J]. 计算机工程与应用, 2012, 48(24): 177-81.
	Cai Hong．SAR image compression based on sparse representation [J]．Computer Engineering and Ap

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed