A note on neurofractal-based defect recognition and classification in nonwoven web images

Payvandy, Pedram; Yousefzadeh, Maryam; Latifi, Masoud

doi:10.1080/00405000802224551

Cited by 7 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ann in conjunction with the imaging technique was used for detecting defects in thermally bonded nonwovens (Payvandy et al, 2008). Polypropylene fibre was used for the sample preparation.…”

Section: 5mentioning

confidence: 99%

“…non-defective, thick area, thin area and neps were taken as the output parameters of the model. Multi-layered feed-forward neural network architecture with a backpropagation algorithm was used for defect classification (Payvandy et al, 2008). The multi-layered neural network consisted of the input layer with three neurons, one hidden layer with six neurons and the output layer with four neurons.…”

Section: 5mentioning

confidence: 99%

See 1 more Smart Citation

Modelling nonwovens using artificial neural networks

Patanaik

Anandjiwala

2011

Soft Computing in Textile Engineering

View full text Add to dashboard Cite

“…Ann in conjunction with the imaging technique was used for detecting defects in thermally bonded nonwovens (Payvandy et al, 2008). Polypropylene fibre was used for the sample preparation.…”

Section: 5mentioning

confidence: 99%

Section: 5mentioning

confidence: 99%

Modelling nonwovens using artificial neural networks

Patanaik

Anandjiwala

2011

Soft Computing in Textile Engineering

View full text Add to dashboard Cite

“…2 P. Payvandy and his collaborators introduced an off-line neuro-fractal method for detection and classification of thermal-bond nonwoven web images using the box counting dimension as the main feature and the BP neural network as classifier. 3 At the level of software systems for vision inspection, the most used commercialized systems for nonwoven defect inspection include SMASH WEB Õ of ISRA VISION, NIS200 Õ of Lenzing Instruments, and FLAWSCANTM 1000 Nonwoven of i2S. These systems can detect common defects like thin areas, thick areas, holes, lines, coating defects, contamination, embossing defects, and so on.…”

Section: Introductionmentioning

confidence: 99%

A comparison of robust Bayesian and LVQ neural network for visual uniformity recognition of nonwovens

Liu

Zuo

Zeng

et al. 2011

Textile Research Journal

View full text Add to dashboard Cite

The visual uniformity recognition of nonwoven materials using image analysis and neural network is a typical application of pattern recognition in textile industry. In this paper, we try to find a solution to this problem by combining the generalized Gaussian density (GGD) model in wavelet domain and two types of neural networks, robust Bayesian and learning vector quantization (LVQ) neural network. The proposed model is constituted with two stages, i.e., texture representation and pattern recognition. For texture representation, each image is decomposed into four levels using the 9-7 bi-orthogonal wavelet base. The wavelet coefficients in each subband are independently modelled by the GGD model. Moreover, taken as textural features, the corresponding scale and shape parameters estimated from the wavelet coefficients distribution with the maximum likelihood (ML) estimation are extracted in order to train and test the neural network for visual uniformity classification. During the pattern recognition part, robust Bayesian neural network and LVQ neural network are used as classifier. Especially, the experiments based on robust Bayesian neural network are taken as the key point. Experimental results indicate that the robust Bayesian neural network perform superiorly.

show abstract

“…Militký and Klicka used the Quadrat method to describe the nonwoven surface uniformity and mass distribution with the variation of gray level images [2]. However, the visual quality recognition of nonwovens by using computer vision and pattern recognition is just at the beginning, especially the comprehensive visual quality evaluation including the structure uniformity and surface defects [3,4,5].…”

Section: Introductionmentioning

confidence: 99%

The Visual Quality Recognition of Nonwovens Using a Novel Wavelet Based Contourlet Transform

Liu

Zuo²

2011

AMR

View full text Add to dashboard Cite

In this paper, a novel wavelet based contourlet transform for texture extraction is presented. In the texture analysis section, we propose a novel wavelet based contourlet transform, which can be considered as a simplified but more sufficient for texture analysis for nonwoven image compared with version of the one introduced by Eslami in theory view. In experiment, nonwoven images of five different visual quality grades, 125 of each grade, are decomposed using wavelet based contourlet transform with ‘PKVA’ filter as the default filter of Laplacian Pyramid (LP) and Directional Filter Bank (DFB) at 3 levels and two energy-based features, norm-1 L1 and norm-2 L2, are calculated from the wavelet coefficients at the first level and contourlet coefficients of each high frequency subband at different levels and directions to train and test SVM. When the nonwoven images are decomposed at 3 levels and 16 L1s are extracted, with 500 samples to train the SVM, the average recognition accuracy of test set is 98.4%, which is superior to the comparative method using wavelet texture analysis.

show abstract

A note on neurofractal-based defect recognition and classification in nonwoven web images

Cited by 7 publications

References 18 publications

Modelling nonwovens using artificial neural networks

Modelling nonwovens using artificial neural networks

A comparison of robust Bayesian and LVQ neural network for visual uniformity recognition of nonwovens

The Visual Quality Recognition of Nonwovens Using a Novel Wavelet Based Contourlet Transform

Contact Info

Product

Resources

About