摘要
为更好地适应机织物纹理以及减少程序的运行时间,选取平纹、斜纹、缎纹3种组织结构采用K-奇异值分解(K-SVD)的方法训练得到一个自适应字典。以峰值信噪比、结构相似性为指标,探讨不同稀疏基数对机织物纹理图像重构的影响,针对不同的应用,选取了合适的稀疏基数T。利用该字典重构机织物纹理图像,在此基础上检测织物瑕疵。实验结果表明:T=6时,算法不仅能有效重构机织物纹理图像(PSNR和SSIM),而且重构效果要优于初始离散余弦转换(DCT)字典;T=4时,K-SVD字典能更好地适应瑕疵样本,且鉴别瑕疵的能力更强。
In order to well adapt the woven fabric texture and reduce the algorithm running time, three basic weave patterns （plain, twill and satin） were chosen as trained samples to learn an adaptive dictionary by K-means singular value decomposition （K-SVD） dictionary learning approach. In order to select appropriate sparsity cardinality T for different applications, peak signal to noise ratio（PSNR） and structural similarity index measurement （SSIM） were chosen as evaluating performance indexes. For regular fabric texture image reconstruction, T = 6, the experimental results demonstrate that the proposed method not only can approximate fabric samples well, but also can improve the quality of reconstructed image （in terms of PSNR and SSIM） , in comparison with discrete cosine transformation dictionary. In addition, for fabric flaw detection, T = 4, the K-SVD can well adapt samples with defects, and has stronger capability of identifying defects, compared with discrete cosine transformation dictionary.
出处
《纺织学报》
EI
CAS
CSCD
北大核心
2018年第2期165-170,共6页
Journal of Textile Research
基金
国家自然科学基金项目(61379011)
关键词
机织物纹理表征
DCT字典
K-SVD字典
瑕疵检测
图像重构
woven fabric texture characterization
discrete cosine transformation dictionary
K-SVD dictionary
defect detection
image reconstruction
