Steel Surface Defect Detection Using a New Haar–Weibull-Variance Model in Unsupervised Manner

Liu, Kun; Wang, Heying; Chen, Haiyong; Qu, Er-Qing; Tian, Ying; Sun, Hexu

doi:10.1109/tim.2017.2712838

Cited by 130 publications

(57 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is hard for Weibull distribution to handle defects with gradual intensity or with low contrast. Hence, Liu et al [91] developed a Haar-Weibull-variance (HWV) model by replacing the features of local gradient magnitude by Haar features from local patches. This method is reported to have achieved an average correct detection rate of 96.2% on a homogeneously textured defect dataset gathered from an actual hot-rolling mill.…”

Section: Active Contour Modelmentioning

confidence: 99%

Automated Visual Defect Detection for Flat Steel Surface: A Survey

Luo

Fang

Liu

et al. 2020

IEEE Trans. Instrum. Meas.

340

111

View full text Add to dashboard Cite

Automated computer-vision-based defect detection has received much attention with the increasing surface quality assurance demands for the industrial manufacturing of flat steels. This paper attempts to present a comprehensive survey on surface defect detection technologies by reviewing about 120 publications over the last two decades for three typical flat steel products of con-casting slabs, hot-and cold-rolled steel strips. According to the nature of algorithms as well as image features, the existing methodologies are categorized into four groups: Statistical, spectral, model-based and machine learning. These literatures are summarized in this review to enable easy referral to suitable methods for diverse application scenarios in steel mills. Realization recommendations and future research trends are also addressed at an abstract level.

show abstract

Section: Active Contour Modelmentioning

confidence: 99%

Automated Visual Defect Detection for Flat Steel Surface: A Survey

Luo

Fang

Liu

et al. 2020

IEEE Trans. Instrum. Meas.

340

111

View full text Add to dashboard Cite

show abstract

“…4. First, given a training set T {ti[r×c] | i=1,2,...,Nt} which is constituted of Nt images with a size of r×c pixel, the pattern label of each center pixel in each image is calculated by using a certain CLBP operator (i.e., (6), or (7), or (8)). Second, the calculated pattern labels are discriminatively kept in the buffer pools according to the pattern uniformity defined in (2).…”

Section: A Dominant Nonuniform Features Pursuingmentioning

confidence: 99%

“…It was driven by hardware acceleration technique and the upper limit of rolling speed was elevated to 20 m/s [4]. Liu et al constructed an unsupervised Haar-Weibull-variance (HWV) model, and a higher TPR of 96.2% was achieved [7].…”

mentioning

confidence: 99%

Generalized Completed Local Binary Patterns for Time-Efficient Steel Surface Defect Classification

Luo

Sun

et al. 2019

IEEE Trans. Instrum. Meas.

129

View full text Add to dashboard Cite

Abstract-Efficient defect classification is one of the most important preconditions to achieve online quality inspection for hot-rolled strip steels. It is extremely challenging owing to various defect appearances, large intra-class variation, ambiguous inter-class distance, and unstable gray values. In this paper, a generalized completed local binary patterns (GCLBP) framework is proposed. Two variants of improved completed local binary patterns (ICLBP) and improved completed noise-invariant local-structure patterns (ICNLP) under the GCLBP framework are developed for steel surface defect classification. Different from conventional LBP variants, descriptive information hidden in nonuniform patterns is innovatively excavated for better defect representation. This work focuses on the following aspects: First, a lightweight searching algorithm is established for exploiting the dominant nonuniform patterns (DNUPs). Second, a hybrid pattern code mapping mechanism is proposed to encode all the uniform patterns and DNUPs. Third, feature extraction is carried out under the GCLBP framework. Finally, histogram matching is efficiently accomplished by simple nearest neighbor classifier (NNC). The classification accuracy and time-efficiency are verified on a widely recognized texture database (Outex) and a real-world steel surface defect database (NEU). The experimental results promise that the proposed method can be widely applied in online AOI instruments for hot-rolled strip steel.Index Terms-Surface defects, image classification, hot-rolled strips, local binary patterns (LBP), automatic optical inspection (AOI) instrument.

show abstract

“…The traditional human inspection system has several disadvantages such as a less-automatic and time-consuming procedure [4,5]. An image-based system, on the other hand, is developed to enable more elaborate, rapid and automatic inspection than the existing methods [6]. Furthermore, it is widely known that the surface defect accounts for more than 90% of entire defects in steel products, e.g., plate and strip [7].…”

Section: Introductionmentioning

confidence: 99%

Steel Surface Defect Diagnostics Using Deep Convolutional Neural Network and Class Activation Map

et al. 2019

View full text Add to dashboard Cite

Steel defect diagnostics is considerably important for a steel-manufacturing industry as it is strongly related to the product quality and production efficiency. Product quality control suffers from a real-time diagnostic capability since it is less-automatic and is not reliable in detecting steel surface defects. In this study, we propose a relatively new approach for diagnosing steel defects using a deep structured neural network, e.g., convolutional neural network (CNN) with class activation maps. Rather than using a simple deep learning algorithm for the classification task, we extend the CNN diagnostic model for being used to analyze the localized defect regions within the images to support a real-time visual decision-making process. Based on the experimental results, the proposed approach achieves a near-perfect detection performance at 99.44% and 0.99 concerning the accuracy and F-1 score metric, respectively. The results are better than other shallow machine learning algorithms, i.e., support vector machine and logistic regression under the same validation technique.

show abstract

Steel Surface Defect Detection Using a New Haar–Weibull-Variance Model in Unsupervised Manner

Cited by 130 publications

References 29 publications

Automated Visual Defect Detection for Flat Steel Surface: A Survey

Automated Visual Defect Detection for Flat Steel Surface: A Survey

Generalized Completed Local Binary Patterns for Time-Efficient Steel Surface Defect Classification

Steel Surface Defect Diagnostics Using Deep Convolutional Neural Network and Class Activation Map

Contact Info

Product

Resources

About