Computer Evaluation Of Fabric Smoothness Rating After Laundering

Appearance of fabric after laundering directly affects the aesthetic characteristics of textiles and is also one of the important indicators of evaluating fabric's easy care characteristic. How to evaluate the grade of fabric smoothness is an important thing of textile testing fields. Domestic fabric smoothness assessment is primarily under the American standard of AATCC 124-2001. Wrinkle properties of the sample will be assessed with standard cards in the standard lighting conditions through visual comparison. The GB/T 13796-1992 is based on the American AATCC standard and still uses the AATCC sample cards, the working environment and assessment methods are similar to AATCC. This method is subjective evaluation and liable to experimental error for human factors. In this paper, the image processing technique is introduced into textile field. The fabric smoothness after laundering is evaluated by computer. It has some impacts on the objective and quick evaluation of the grade of fabric smoothness.In this paper, several methods based on image technologies, which make use of newly developed theories in information science, such as two-dimensional wavelet transform, are used to analysis knitted fabric and woven fabric smoothness in order to acquire the finer image information. Firstly, fabric image is pretreated and decomposed by wavelet transform; meanwhile, high frequency information is extracted. Secondly, four kinds of wrinkle feature parameters are applied to calculate the feature values of fabric smoothness with different smoothness templates. Finally, smoothness grade of different types of fabrics can be evaluated according to this result through using minimum distance classification. For describing the assessment result quantitatively, the correlation coefficient is calculated between objective assessment and subjective assessment to validate the feasibility of this method. The main contents of this thesis are briefly summarized as follows:(1) The objective evaluation system of fabric smoothness rating has been developed, which integrates the image process and analysis program with the image-capturing device. The entire system is consisted of hardware section and software section. The hardware section includes fabric image acquisition device; the software section is based on object-oriented programming ideas, using Visual C + + 6.0 programming environment and Matlab software to complete the calculation.(2) The application software has been programmed. The chief program has a friendly user interface, i.e., capturing and reading of image, pretreatment and wavelet analyses, extraction and database preservation of the feature parameters, with which fabric image can be captured, analyzed and processed conveniently.(3) Three different methods are used to make the fabric pretreatment of the collecting images. They are Median filter, Gaussian smoothing and Median filter & gradient sharpening.(4) Fabric image can be decomposed by wavelet transform; meanwhile, high frequency information is extracted. Four kinds of wrinkle feature parameters are applied to calculate the fabric smoothness feature values with different smoothness templates. It has realized digital image processing of the fabrics' information and effectively avoided human factors in the subjective assessment.(5) The experiment has been carried out on the objective evaluation system developed in this thesis by selecting 29 actual fabrics (16 knitted fabrics and 13 woven fabrics). Experiments show that different method of pretreatment will affect the results of objective assessment and Median filter is better than other methods. Minimum distance classification is used to evaluate the smoothness grade of different types of fabrics. The correlation coefficient between the subjective assessment and objective assessment reached 95.06% and 91.17% respectively. The research results indicate that this method is feasible.