Objective evaluation of fabric pilling based on wavelet transform and the local binary pattern

Jing, Junfeng; Zhang, Zanzan; Kang, Xuejuan; Jia, Jianyuan

doi:10.1177/0040517512449049

Cited by 27 publications

(32 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, prediction of fabric elongation, 25 drying times of bobbins, 4 fabric pilling, 39 the air permeability of fabrics. 15 • Construction of models to reduce the consumption of textile-related materials, such as fabrics, yarns, dyes, and sewing threads 5 • Discovering patterns that can be used to produce better textile endproducts 13,61,68 • Analyzing textile data to achieve better customer satisfaction…”

Section: Advantages Of Dm Enabled In Textile Industrymentioning

confidence: 99%

“…33,35 Another technical difficulty in textile studies is to determine independent parameters from the training data to reduce the dimensionality of the feature vector, improving the speed of the evaluation and accuracy through this way. To solve this problem, several textile studies 35,39,40 used the PCA technique.…”

Section: Support Vector Machine In Textile Industrymentioning

confidence: 99%

“…The third problem is that textile data may have numerous features in dimension, and many of these features may be irrelevant or redundant. In this case, PCA 29,35,39,40,47 or filterbased feature selection 4 methods can be used to reduce the dimensionality before applying the KNN algorithm. The last challenge is to identify the weights of features if the different importance of variables is taken into consideration.…”

Section: K-nearest Neighbor In Textile Industrymentioning

confidence: 99%

See 2 more Smart Citations

Data mining and machine learning in textile industry

Yıldırım

Birant

Alpyıldız

2017

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Data mining has been proven useful for knowledge discovery in many areas, ranging from marketing to medical and from banking to education. This study focuses on data mining and machine learning in textile industry as applying them to textile data is considered an emerging interdisciplinary research field. Thus, data mining studies, including classification and clustering techniques and machine learning algorithms, implemented in textile industry were presented and explained in detail in this study to provide an overview of how clustering and classification techniques can be applied in the textile industry to deal with different problems where traditional methods are not useful. This article clearly shows that a classification technique has higher interest than a clustering technique in the textile industry. It also shows that the most commonly applied classification methods are artificial neural networks and support vector machines, and they generally provide high accuracy rates in the textile applications. For the clustering task of data mining, a K-means algorithm was generally implemented in textile studies among the others that were investigated in this article. We conclude with some remarks on the strength of the data mining techniques for textile industry, ways to overcome certain challenges, and offer some possible further research directions.

show abstract

Section: Advantages Of Dm Enabled In Textile Industrymentioning

confidence: 99%

Section: Support Vector Machine In Textile Industrymentioning

confidence: 99%

Section: K-nearest Neighbor In Textile Industrymentioning

confidence: 99%

See 1 more Smart Citation

Data mining and machine learning in textile industry

Yıldırım

Birant

Alpyıldız

2017

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…The results of their study indicated that the ANN had a high prediction rate for woolen fabrics. Jing et al [22] developed a predictive model for the wrinkling appearance of fabric using modified wavelet coefficients and optimized SVM classifications.…”

Section: Related Workmentioning

confidence: 99%

Discovering the relationships between yarn and fabric properties using association rule mining

Yıldırım¹,

Birant²,

Alpyıldız³

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:Investigation of the effects of yarn parameters on fabric quality and finding important parameters to achieve desired fabric properties are important issues for the design process with the aim to meet the needs of the textile industry and the consumer for complex and specific requirements of functionality. Despite many statistical and mathematical studies that predict and reveal specific properties of utilized yarn and fabric materials, a number of challenges continue to exist when evaluated in many perspectives, such as discovering complex relationships among material properties in data. Data mining plays an important role in discovering hidden patterns from fabric data and transforming it into knowledge. Therefore, the aim of the study is to uncover relationships between yarn parameters and fabric properties using an extended FP-Growth algorithm in association rule mining. This study extracts different types of frequent itemsets (closed, maximal, top-k, top-k closed, top-k maximal) that have not been determined in textile sector before.This article also proposes two novel concepts, closed frequent item and maximal frequent item, to identify significant items in data. In the experimental studies, the algorithm was executed on a real-world textile dataset with different support threshold values to compare the different types of patterns. Experimental results show that proposed approach is very useful for discovering rules related to yarn and fabric properties.

show abstract

“…The wavelet transform not only contains the localization idea of short time Fourier transform, but also overcomes the defect that the window size cannot vary with frequency. The resolution is good at high and low frequencies; it is an ideal signal processing mode [21].…”

Section: Wavelet Theorymentioning

confidence: 99%

Recognition of fault process parameters for diameter uniformity variation in melt spinning

Kuo

Huang

et al. 2014

Fibers Polym

View full text Add to dashboard Cite

This study focused on the abnormal condition of diameter variation in melt spinning, and attempted to recognize the machine processing parameter that deviates from the set value. The experiment used polypropylene as the experimental material. The machine processing parameters included nine factors, including temperatures in three extruder barrel sections, temperature of metering pump, die temperature, spinneret temperature, speed of an extruder screw, speed of metering pump and speed of take-up roll. The biaxial laser sensor measured the yarn diameter instantly, and the optimum parameter combination for minimum diameter variation was obtained by Taguchi method and analysis of variance (ANOVA). The degree of influence of various processing parameters on the diameter variation was determined. The optimum parameter combination was used as parameter setting value, and the processing parameters of various factors were changed for experiment, so as to obtain the signals of abnormal condition. Two methods were used for feature extraction. The minimum entropy of wavelet transform signal was used as eigenvector, and two features were selected by analyzing the statistical process control chart, which are skewness and kurtosis. The abnormal processing parameters and normal condition were recognized effectively and accurately by using the three eigenvalues and back-propagation neural network. With enough training samples, the recognition success rate was as high as 100 %. For complete abnormity diagnosis of melt spinning machine, a two-factor classification process was established by using the single-factor classification result and backpropagation neural network. The experimental results proved that the proposed method can recognize various abnormal conditions successfully and effectively.

show abstract

Objective evaluation of fabric pilling based on wavelet transform and the local binary pattern

Cited by 27 publications

References 19 publications

Data mining and machine learning in textile industry

Data mining and machine learning in textile industry

Discovering the relationships between yarn and fabric properties using association rule mining

Recognition of fault process parameters for diameter uniformity variation in melt spinning

Contact Info

Product

Resources

About