Evaluation of the wear label description in carpets by using local binary pattern techniques

Abstract

Carpet manufacturers certify their products for end-use applications by evaluating the wear behavior of their carpets in mechanical experiments. Currently, this process is performed by visual inspection, suffering from subjective gathers that limit reliability. To automate this process, we propose the use of image processing techniques, specifically of local binary pattern (LBP) statistics. Such statistics are tolerant against illumination changes, can be easily implemented, and perform well when combined with a symmetrized adaptation of the Kullback—Leibler divergence. As a main innovation, we extend the existing rotationally invariant LBPs by including ‘mirror’ and ‘complement’ invariants. We show an accurately improved and more reliable estimation of the degree of wear in worn carpets. The evaluation is performed on four digital reference scales, each containing eight pairs of images comparing transitional degrees of wear to the original appearance. Additionally, the texture changes due to distortions of the pile yarn tufts are enhanced by choosing a suitable scale factor per reference. We validate the findings using six physical reference scales, each containing four pairs of images. In both references, linear correlations of over 0.89 are demonstrated between the degrees of wear and extracted features from the images. These findings justify the use of the proposed LBP extensions in a first approach towards an automated low-cost inspection system for carpet wear at low computation cost.

Optimizing feature extraction in image analysis using experimented designs: a case study evaluating texture algorithms for describing appearance retention in carpets

“…Other columns are filled with zeros. The parameter of a factor level is calculated as the difference between the mean value of its associated observations and the overall mean as in Equation 17. Whereρ(X x ) is the mean value of the observations in which the level x of the factor X, for any of the experimental factors, is applied.…”

Quantifying Appearance Retention in Carpets Using Geometrical Local Binary Patterns

“…Several studies based on computer vision have been aimed to quantify the AR grades objectively [5][6][7][8][9]. They still are not good enough to meet the required discrimination of the AR grades imposed by standards on a sufficient wide of carpets [10].…”

“…Algorithms based on Local Binary Pattern techniques have shown promising results to achieve this goal [9]. LBP techniques first describe with binary codes the changes in intensity values around a neighbourhood for each pixel in an image [13].…”

“…Assigning code numbers to the binary codes, the texture is statistically characterized by the probability of occurrence of the possible code numbers in the image. Grouping symmetric invariants of binary codes by using points on a circular neighbourhood improves the distinction of similar textures such as those exhibit by consecutive AR grades [9]. Also, relevant changes in appearance are better characterized by computing binary codes at different radii depending of the type of carpet [13].…”

“…The GLBP technique is compared with an invariant rotational mirror based LBP technique [9] called in this paper symLBP. symLBP was our previous improvement to distinguish AR grades in carpets.…”