Improving Automatic Detection of Defects in Castings by Applying Wavelet Technique

Li, Xiaoli; Tso, S.K.; Guan, Xinping; Huang, Qian

doi:10.1109/tie.2006.885448

Cited by 140 publications

(60 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…How to extract a set of better feature representations and design the appropriate classifier for surface defects has been a hot research topic for many years. [1][2][3][4][5][6][7][8] A lot of methods about feature extraction and classification for image have been developed [9][10][11][12][13][14][15][16][17] , M. X. Chu et al 16 extracted features of geometry, gray, projection, texture and frequency-domain of defect in steel, then an enhanced twin support vector machine was adopted to realize the classification. A. Cord et al 12 proposed a classification method of statistical learning based on a textural feature for defect of metallic surface.…”

Section: Introductionmentioning

confidence: 99%

“…S. Ghorai 7 derived a set of good-quality defect descriptors from wavelet feature set and applied support vector machine to the classification and detection of the defects. These traditional methods usually use handcrafted features, such as geometrical shape 11,13,15,16 , grayscale 1,13,16 , texture 3,[10][11][12] , local binary pattern 8 , wavelet transform [4][5][6][7]9 or their combinations 2,11,16 , followed by a trainable classifier, such as artificial neural networks 9,11,14 , support vector machine [6][7][8]13,15 and so on. They mainly include three stages: 1) Locating the position of surface defects (Detection).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of surface defects on steel sheet using convolutional neural networks

Zhou¹,

Chen²,

Zhang³

et al. 2017

Mater. Tehnol.

107

View full text Add to dashboard Cite

A convolutional neural network (CNN) is proposed to learn multiple useful feature representations for a classification from low level (raw pixels) to high level (object). Convolutional kernels are initialized by the learned filter kernels that come from sparse auto-encoders. Unlike some traditional methods, which divide the feature abstracting and classifier training into two separated processes, a discriminative feature vector and a single multi-class classifier of softmax regression are learned simultaneously during the training process. Based on the learned high-quality feature representation, the classification can be efficiently performed. A real-world case of surface defects on steel sheet, which evaluates the classification performance of the proposed method, is depicted in detail. The experimental results indicate that the proposed method is quite simple, effective and robustness for the classification of surface defects on hot-rolled steel sheet. Keywords: convolutional neural networks, classification, surface defects, steel sheet, convolutional kernels, sparse auto-encoder Konvolucijska nevronska mre`a (CNN) je predlagana za u~enje {tevilnih koristnih predstavitev pri klasifikaciji od nizkega nivoja (grobe slikovne pike) do visokega nivoja (predmet). Konvolucijska jedra so inicializirana z nau~enimi filtrirnimi jedri, ki izhajajo iz redkih samoenkoderjev. Razli~no od nekaterih klasi~nih metod, ki delijo funkcijo abstrakcije in trening klasifikacije v dva lo~ena procesa, se vektor nediskriminativne funkcije v enostavnem ve~razrednem klasifikatorju regresije softmax, u~i hkrati med procesom treninga. Na osnovi nau~ene predstavitve z visoko kvalitetno funkcijo, se lahko klasifikacija u~inkovito izvede. Primer iz resni~nega sveta povr{inske napake na jekleni plo~evini, ki ocenjujejo zmogljivost klasifikacije je prikazan v podrobnostih. Rezultati eksperimentov ka`ejo, da je predlagana metoda razmeroma preprosta, u~inkovita in robustna pri klasifikaciji povr{inskih napak na vro~e valjani jekleni plo~evini.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of surface defects on steel sheet using convolutional neural networks

Zhou¹,

Chen²,

Zhang³

et al. 2017

Mater. Tehnol.

107

View full text Add to dashboard Cite

show abstract

“…As a result, a thicker or/and denser sample will generate a darker area in the image corresponding to the higher X-ray absorption. Therefore, defects are characterized in the X-ray images by local changes in the image intensity, resulting in the corresponding local discontinuities in the gray values of the acquired image [11]. When a defect occurs in a product (such as a crack in a casting), the resulting X-ray image will show some areas with local gray level changes in the image, which tells us that something has happened inside the product.…”

Section: A Typical 2d X-ray Systemmentioning

confidence: 99%

A Robust Crack Filter Based on Local Gray Level Variation and Multiscale Analysis for Automatic Crack Detection in X-ray Images

Peng¹,

Nam²

2016

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-Internal cracks in products are invisible and can lead to fatal crashes or damage. Since Xrays can penetrate materials and be attenuated according to the material's thickness and density, they have rapidly become the accepted technology for non-destructive inspection of internal cracks. This paper presents a robust crack filter based on local gray level variation and multiscale analysis for automatic detection of cracks in X-ray images. The proposed filter takes advantage of the image gray level and its local variations to detect cracks in the X-ray image. To overcome the problems of image noise and the non-uniform intensity of the X-ray image, a new method of estimating the local gray level variation is proposed in this paper. In order to detect various sizes of crack, this paper proposes using different neighboring distances to construct an image pyramid for multiscale analysis. By use of local gray level variation and multiscale analysis, the proposed crack filter is able to detect cracks of various sizes in X-ray images while contending with the problems of noise and non-uniform intensity. Experimental results show that the proposed crack filter outperforms the Gaussian model based crack filter and the LBP model based method in terms of detection accuracy, false detection ratio and processing speed.

show abstract

“…Yong-Ju JEON, 1) Doo-chul CHOI, 1) Jong Pil YUN 2) and Sang Woo KIM 1) * specific type of defect and material.…”

Section: Detection Of Periodic Defects Using Dual-light Switching Ligmentioning

confidence: 99%

“…However, steel manufacturing processes create a difficult environment for defect inspection because of the hot-rolling processes that involve continuous casting and rolling. Therefore, many inspection steps are manually performed by humans 1) or occasional inspections. In steel manufacturing conditions, many methods have been developed to improve the quality of steel and achieve automatic inspection.…”

Section: Introductionmentioning

confidence: 99%

Detection of Periodic Defects Using Dual-Light Switching Lighting Method on the Surface of Thick Plates

et al. 2015

View full text Add to dashboard Cite

Currently, automated inspection algorithms are widely used to ensure high-quality products and achieve high productivity in the steel making industry. In this paper, we propose a vision-based method to detect periodic defects in the surface of thick plates. To minimize the influence of a non-uniform surface property and improve the accuracy of the detection rate, a detection method based on dual-light switching lighting (DLSL) proposed. In general, single lighting (SL) methods cannot well represent the steel surface because the surface features are not uniform and strongly vary according to lighting conditions. In the DLSL method, defective regions are represented by a black and white pattern, regardless of shape, size, or orientation. Therefore, defects can be found by the black and white patterns in the corresponding images. Gabor filtering was used to find defective regions and reduce the false positive rates. To find the periodic candidates of defects, we process the period searching using manufacturing information. To identify periodic defects from among the defect candidates, we use "similarity of shapes" features with a support vector machine (SVM) classifier. The experimental results show that the proposed algorithm is effective at detecting periodic defects on the surface of thick plates.

show abstract

Improving Automatic Detection of Defects in Castings by Applying Wavelet Technique

Cited by 140 publications

References 17 publications

Classification of surface defects on steel sheet using convolutional neural networks

Classification of surface defects on steel sheet using convolutional neural networks

A Robust Crack Filter Based on Local Gray Level Variation and Multiscale Analysis for Automatic Crack Detection in X-ray Images

Detection of Periodic Defects Using Dual-Light Switching Lighting Method on the Surface of Thick Plates

Contact Info

Product

Resources

About