The influence of gray‐level co‐occurrence matrix variables on the textural features of wrinkled fabric surfaces

Abstract

The gray‐level co‐occurrence matrix (GLCM), or gray‐level spatial dependence matrix, constitutes one of the most important algorithms capable of identifying the repetition, uniformity, disorder, contrast, gray‐tone linear dependencies, and heterogeneity of textural features of various surfaces. In this study, to evaluate the wrinkle grade of textile fabrics, the GLCM from an image of a wrinkled fabric surface is established and examined in terms of the spatial displacement of its pixel pairs, the number of gray levels, and the angle orientations. The statistical textural features calculated from the GLCM include five metrics designated as energy, contrast, correlation, entropy, and inverse difference moment. It is revealed from the analysis that for a fresh wrinkle‐free fabric surface, the periodicity of the surface geometry dictates the image textural features through alternation in the spatial displacement of the pixel pairs, whereas for wrinkled fabrics, our results show a highly correlated relationship between the objective wrinkle measurement of textural features and the subjective evaluations performed by expert panels. Among the five textural features, the best correlation was obtained between the inverse difference moment and the visual subjective scores, with a correlation coefficient as high as 0.993.