Adaptive neuro-fuzzy system for quantitative evaluation of woven fabrics' pilling resistance

Considered the texture features of the fabric images to quantize its pilling for the first time.Introduced a method for creating sampling dataset required in building the soft-computing classifier.Utilized the neuro-fuzzy classification system to approach the high level of human beings.Created a user-friendly GUI that integrates the main four stages of pilling evaluation. Fabric pilling is considered a performance and aesthetic property of the woven products that determine its quality. The subjective evaluation of the fabric pilling results in misleading values that depend on the measurement standard even for the same sample. This work utilizes some textural features extracted from the fabric's images to obtain better representative and quantitative values of the fabric's surface. An algorithm for creating features dataset for training and testing the soft-computing classifier was described where random noise was added to the limited number of fabric's pilling standard images. The objective pilling classification of the fabric samples was performed using an adaptive neuro-fuzzy system (ANFIS) which showed an ability to classify the noised standard images with a correct classification rate of 85.8%. The ANFIS was also able to classify actual fabric samples with a Spearman's coefficient of rank correlation at +0.985 when compared with the classification grades of the human operators. Results showed high efficiency of the system that is independent on the different fabric structure or color which suggests its availability to replace the currently applied subjective pilling evaluation.

[1]  I. Jasińska,et al.  Assessment of a fabric surface after the pilling process based on image analysis , 2009 .

[2]  António de Oliveira Mendes,et al.  Subjective and Objective Pilling Evaluations of Textile Fabrics: A Comparison , 2010 .

[3]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[4]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[5]  Paulo Torrão Fiadeiro,et al.  Virtual subjective pilling evaluation: an alternative , 2011 .

[6]  Xungai Wang,et al.  Objective Classification of Fabric Pilling Based on the Two-Dimensional Discrete Wavelet Transform , 2003 .

[7]  Sungmin Kim,et al.  Development of an objective fabric pilling evaluation method. I. Characterization of pilling using image analysis , 2013, Fibers and Polymers.

[8]  Jinlian Hu,et al.  Objective Evaluation of Fabric Pilling Using Image Analysis Techniques , 2002 .

[9]  Dariush Semnani,et al.  Detecting and Measuring Fabric Pills Using Digital Image Analysis , 2009 .

[10]  Koichiro Toriumi,et al.  Evaluation of Pilling by Means of Computer Image Analysis , 1988 .

[11]  Tae Jin Kang,et al.  Image Analysis of Standard Pilling Photographs Using Wavelet Reconstruction , 2005 .

[12]  Zhi-Tao Xiao,et al.  Fabric Pilling Segmentation Based on Edgeflow Algorithm , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[13]  Liu Xiaojun,et al.  Segmentation for Fabric Pilling Images Based on Edge Flow , 2009, 2009 Second International Conference on Information and Computing Science.

[14]  Ebraheem Shady,et al.  Application of Principal Component Analysis to Boost the Performance of an Automated Fabric Fault Detector and Classifier , 2014 .

[15]  Xungai Wang,et al.  New Methods for Objective Evaluation of Fabric Pilling by Frequency Domain Image Processing , 2009 .

[16]  António de Oliveira Mendes,et al.  Optical Estimation of a Set of Pilling Coefficients for Textile Fabrics , 2009 .

[17]  Xia Chen,et al.  Evaluating Fabric Pilling with Light-Projected Image Analysis , 2004 .

[18]  Chang H. Hsi,et al.  Characterizing Fabric Pilling by Using Image-analysis Techniques. Part I: Pill Detection and Description , 1998 .

[19]  B. K. Behera,et al.  Objective measurement of pilling by image processing technique , 2005 .

[20]  Soae L. Paek,et al.  Pilling, Abrasion, and Tensile Properties of Fabrics from Open-End and Ring Spun Yarns 1 , 1989 .

[21]  Sayed Ibrahim,et al.  A dynamic and robust image processing based method for measuring the yarn diameter and its variation , 2014 .

[22]  Xungai Wang,et al.  Objective pilling evaluation of nonwoven fabrics , 2010 .

[23]  María S. Millán,et al.  Automatic method based on image analysis for pilling evaluation in fabrics , 1998 .

[24]  Junmin Zhang,et al.  Objective Grading of Fabric Pilling with Wavelet Texture Analysis , 2007 .

[25]  Jyh-Shing Roger Jang,et al.  Self-learning fuzzy controllers based on temporal backpropagation , 1992, IEEE Trans. Neural Networks.

[26]  Xungai Wang,et al.  Characterization and application of objective pilling classification to patterned fabrics , 2005 .

[27]  Azriel Rosenfeld,et al.  A Comparative Study of Texture Measures for Terrain Classification , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[28]  Stuart Palmer,et al.  Objective Pilling Evaluation of Wool Fabrics , 2007 .

[29]  Tae Jin Kang,et al.  Objective Evaluation of Fabric Pilling Using Stereovision , 2004 .

[30]  Chang H. Hsi,et al.  Characterizing Fabric Pilling by Using Image-analysis Techniques. Part II: Comparison with Visual Pill Ratings , 1998 .

[31]  Mohamed Eldessouki,et al.  Integrated Computer Vision and Soft Computing System for Classifying the Pilling Resistance of Knitted Fabrics , 2014 .