Intelligent Real-Time Fabric Defect Detection

Castilho, Hugo Peres; Gonçalves, Paulo J. S.; Pinto, J. R. Caldas; Serafim, António Limas

doi:10.1007/978-3-540-74260-9_115

Cited by 10 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Neural networks [116] A total of 128 images 86.2% [117] Unknown Unknown Unknown [118] 0 160 91.88% [119] 0 240 94.38% [120] 0 32 91% (hole), 100% (oil stain) [121] Unknown Unknown 99% [122] 0 270 83.4%…”

Section: Other Methods For P1 Groupmentioning

confidence: 99%

“…Though the detection accuracies in [118][119][120] were high, the image sampling quality was poor and the reliability was unknown. A NN method [121] achieved over 99.9% accuracy in both off-line (2 plain weave fabric samples of unknown sizes) and on-line (a fabric sample of unknown size) defect detections. However, without accurate sample size, the result in [121] was not suitable for comparison.…”

Section: Neural Networkmentioning

confidence: 98%

“…A NN method [121] achieved over 99.9% accuracy in both off-line (2 plain weave fabric samples of unknown sizes) and on-line (a fabric sample of unknown size) defect detections. However, without accurate sample size, the result in [121] was not suitable for comparison. Lastly, a recent radial basis function method [122], using the same feature extraction mask as in [117], achieved 83.4% defect classification for 270 images, although it is not promising compared to other NN methods.…”

Section: Neural Networkmentioning

confidence: 98%

See 2 more Smart Citations

Automated fabric defect detection—A review

Ngan

Pang

Yung

2011

Image and Vision Computing

431

190

View full text Add to dashboard Cite

Section: Other Methods For P1 Groupmentioning

confidence: 99%

Section: Neural Networkmentioning

confidence: 98%

Section: Neural Networkmentioning

confidence: 98%

See 1 more Smart Citation

Automated fabric defect detection—A review

Ngan

Pang

Yung

2011

Image and Vision Computing

431

190

View full text Add to dashboard Cite

“…The number of rules, K, and the antecedent fuzzy sets A ij are determined by means of fuzzy clustering in the product space of the inputs and the outputs (Castilho, Goncalves, Pinto, & Serafim, 2007). To obtain each estimated output,ŷ, Eqs.…”

Section: Fuzzy Modelsmentioning

confidence: 99%

Computational intelligence applied to discriminate bee pollen quality and botanical origin

et al. 2018

View full text Add to dashboard Cite

a b s t r a c tThe aim of this work was to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), and support vector machines (SVM) to predict physicochemical composition of bee pollen mixture given their botanical origin. To obtain the predominant plant genus of pollen (was the output variable), based on physicochemical composition (were the input variables of the predictive model), prediction models were learned from data. For the inverse case study, input/output variables were swapped.The probabilistic NN prediction model obtained 98.4% of correct classification of the predominant plant genus of pollen. To obtain the secondary and tertiary plant genus of pollen, the results present a lower accuracy.To predict the physicochemical characteristic of a mixture of bee pollen, given their botanical origin, fuzzy models proven the best results with small prediction errors, and variability lower than 10%.

show abstract

“…Even though flaw detection literature is manifold, few publications actually discuss both, the entire AVI framework including mechanical construction, controlling, illumination and the algorithmic part: Mak et al [4] present a system based on Gabor filtering with little details given about the mechanical part. In [5], a system based on neural networks is presented, again very little detail is spent on mechanics, illumination or controlling. Sari-Sarraf [6] touches the problem of vibration free image acquisition and evaluation and Stojanovic et.…”

Section: Introductionmentioning

confidence: 99%

A vision based system for high precision online fabric defect detection

Schneider

Holtermann

Neumann

et al. 2012

2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA)

View full text Add to dashboard Cite

A prototype system for automatic in-line flaw detection in industrial woven fabrics is presented. Where state of the art systems operate on low-resolved (≈ 200 ppi) image data, we describe here the process flow to segment single yarns in high-resolved (≈ 1000 ppi) textile images. This work is partitioned into two parts: First, mechanics, machine integration, vibration cancelling and illumination scenarios are discussed based on the integration into a real loom. Subsequently, the software framework for high precision fabric defect detection is presented. The system is evaluated on a database of 54 industrial fabric images, achieving a detection rate of 100% with minimal false alarm rate and very high defect segmentation quality.

show abstract

Intelligent Real-Time Fabric Defect Detection

Cited by 10 publications

References 15 publications

Automated fabric defect detection—A review

Automated fabric defect detection—A review

Computational intelligence applied to discriminate bee pollen quality and botanical origin

A vision based system for high precision online fabric defect detection

Contact Info

Product

Resources

About