Preliminary validation of a fabric smoothness assessment system

I N T R O D U C T I O N The overall quality of a fabric is dependent on a number of factors, including tensile strength, shrinkage, abrasion resistance, and fabric construction. Also among these is the fabric’s tendency to wrinkle after home laundering – referred to as smoothness. The protocol for ascertaining smoothness grade of a fabric is outlined in the American Association of Textile Chemists and Colorists (AATCC) Test Method (TM) 1241. This standard test is designed to evaluate the smoothness of fabric specimens after repeated home laundering. Once three specimens, called swatches, per fabric have been through 5 standard washingdrying cycles, three technicians visually evaluate them. For these evaluations, the specimen is laid on a solid surface that stands at an incline of 5 degrees from vertical under specified lighting conditions. The specimen is then compared to six standard replicas, which are 3-D plastic models, showing varying degrees of smoothness (Figure 1) and having grades 1 (very wrinkly), 2, 3, 3.5, 4, and 5 (very smooth). The Beside exhibiting interand intra-subject variability and being an expensive process, the current smoothness grading system is very inadequate in its ability to provide a true surface description of the fabric. It is, therefore, desirable to develop a system to accurately quantify surface smoothness in a practical and repeatable manner. Previous research efforts have focused on this goal with limited success. These works include ascertaining fabric smoothness by observing surface and shade area ratios from images obtained from a color flatbed scanner2, using laser-triangulation with a rotating stage and neural network classifier3, as well as using stereo imaging with fractal geometry4. Although interesting in their own right, these systems either fail to capture or to describe the 3-D nature of wrinkles and creases that ultimately characterize the fabric’s degree of smoothness. In a previous work we introduced a system based on a smart CMOS camera combined with a laser-line projector to obtain range images of fabric samples5. Because these range images provide an excellent depiction of the surface topography of fabric specimens, by using the facet model6 and the integrated directional derivative gradient (IDDG) operator7, we can locate and quantitatively describe various types of wrinkles using cross-sectional wrinkle profiles. In this paper, we present our to-date progress in the design, development, and testing of this system and outline the preliminary steps towards a large-scale validation of its performance. To that end, results of the A fabric’s tendency to wrinkle is vitally important to the textile industry as it impacts the visual appeal of apparels. Current methods of grading this characteristic, called fabric smoothness, are very subjective and inadequate. As such, a quantitative method for assessing fabric smoothness is of the utmost importance to the textile community. To that end, we have proposed a laser-based surface profiling system that utilizes a smart camera to sense the 3-D topography of the fabric specimens. The system incorporates methods based on anisotropic diffusion and the facet model for characterizing edge information that ultimately relate to a specimen’s degree of wrinkling. In this paper, we detail the initial steps in a large-scale validation of this system. Using histograms of the extracted features, we compare the output of the system among 78 swatches of various color, type, and texture. The results show consistency among repeated scans of the same swatch as well as among different swatches taken from the same fabric sample. The fact that swatches taken from same piece of fabric typically wrinkle similarly adds to the feasibility of the system. In other words, it adequately identifies and measures appropriate features of the wrinkles found on a sample. specimen is assigned the grade of the replica it most closely resembles. Figure 1 Images of the six replicas 1 2 3