Classification of Surface Defects on Steel Strip Images using Convolution Neural Network and Support Vector Machine

Boudiaf, Adel; Benlahmidi, Said; Harrar, Khaled; Zaghdoudi, Rachid

doi:10.1007/s11668-022-01344-6

Cited by 31 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Di et al [22], also adopts the semi-supervised learning approach to build a classification system for steel surface defects and named it CAE-SGAN, as it is based on Convolutional Autoencoder (CAE) and semi-supervised Generative Adversarial Networks (SGAN). Boudiaf et al [23] adopted AlexNet base-model as features extractor and SVM algorithm to classify six kinds of typical surface defects of hot-rolled steels according to the extracted features. Feng et al [24] employed the RepVGG algorithm along with a spatial attention mechanism (RepVGG+SA) to classify defects in the X-SDD dataset.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Steel surface defect recognition using classifier combination

Zaghdoudi,

Bouguettaya,

Boudiaf

2024

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

The quality control of steel products' surface is of utmost importance, where several inspection techniques and technologies were proposed over the last few years. Traditional manual inspection procedures are facing several limitations and often fall short in ensuring flawlessness. Visionbased strategies for automatic steel surface inspection have emerged as powerful and effective tools to solve various industrial-related problems, including products quality control. Therefore, the current study aims to improve the recognition rate of steel surface defects classification system by introducing a novel classifier combination approach. The proposed system utilizes two distinct feature sets, namely LCCMSP and DCP, which were carefully selected based on a comprehensive comparative study of 19 state-of-the-art texture descriptors, considering both accuracy and time consumption. These generated features are individually fed to two classifiers, SVM and RF, leading to the creation of four base classifiers. In the final step, the Bayesian fusion rule is applied to integrate the outputs of these classifiers, ultimately providing the definitive classification decision. To evaluate the proposed system, two steel surface defects datasets, NEU-CLS and X-SDD, are utilized. The experimental results demonstrate that the proposed combination approach surpasses classical combination methods achieving remarkable outcomes compared to existing steel surface defects classification approaches. This highlights the effectiveness and superiority of the proposed system in accurately identifying and classifying steel surface defects while maintaining fast execution time.

show abstract

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Steel surface defect recognition using classifier combination

Zaghdoudi,

Bouguettaya,

Boudiaf

2024

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep CovNet has been hybridized with support vector machines to achieve optimal results in different application areas. For instance, AlexNet Covnet was hybridized with SVM to recognise surface defects in the images of hot-rolled steel strips (Adel et al, 2022). Hameed et al (2018) also employed the feature extraction strength of AlexNet and the classification capability of a modified SVM called Error Correcting Output Code SVM (ECOC-SVM) to classify skin images into five different classes.…”

Section: Hybrid Models and Their Potential In Advancing Deep Learningmentioning

confidence: 99%

Deep Learning: Historical Overview from Inception to Actualization, Models, Applications and Future Trends

Ekundayo,

Ezugwu

2024

Preprint

View full text Add to dashboard Cite

Deep learning stands at the forefront of contemporary machine learning techniques and is well-known for its outstanding predictive accuracy, adaptability to data variability, and remarkable ability to generalize across diverse domains. These attributes have spurred rapid progress and the emergence of novel iterations within the discipline. Yet, this swift evolution often obscures the foundational breakthroughs, with even trailblazing researchers at risk of fading into obscurity despite their seminal contributions. This study aims to provide a historical narrative of deep learning, tracing its origins from the cybernetic era to its current state-of-the-art status. We critically examine the contributions of individual pioneer scholars who have profoundly influenced the development of deep neural networks under the taxonomy of supervised, unsupervised, and reinforcement learning. Furthermore, the study also discusses the trending deep neural network architectures, explaining their operational principles, confronting associated challenges, exploring real-world applications, and outlining potential future trajectories that could offer a starting point for aspiring researchers in the field.

show abstract

“…The columns are the actual class while the rows are the predicted class, and the performance of the classifier is usually evaluated using the data contained in the matrix. 7,27 The confusion matrix of the proposed model K-CV SVM is as Table 6. In order to evaluate the performance of the classifier, four metrics of accuracy, precision, recall, and F1 score is calculated.…”

Section: Experiments and Analysismentioning

confidence: 99%

“…In this context, many researchers have put forward various artificial intelligence algorithms to detect all kinds of surface damage, such as K-nearest neighbor (KNN), 3 artificial neural networks (ANN), 4 SVM, 5 and Self-Organizing Maps (SOM). 6,7 Many researchers have proposed models for metal surface defect detection. Liu et al 8 employed SOM as a classifier and achieved a classification accuracy of 87%.…”

Section: Introductionmentioning

confidence: 99%

Research on surface defect identification of steel balls based on improved K-CV parameter optimization support vector machine

Li,

Ren,

Feng

2023

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Surface defects generated during the production process of steel balls can lead to bearing failures, which makes it crucial to promptly detect and classify these defects. Defects classify is helpful for analysis and improving the production process. An algorithm that incorporates K-fold cross-validation (K-CV) with improved grid search is proposed to optimize the parameters of SVM, in order to detect surface defects with steel balls. Principal Component Analysis (PCA) was employed to reduce the dimensionality of the effective features data. The K-CV algorithm was employed in conjunction with an improved grid search method to find the optimal parameters “c” and “g.” This approach not only reduced the search time but also diminished the influence of individual samples on the model, thereby enhancing its robustness and ultimately improving the classification accuracy. The model’s performance was evaluated using a confusion matrix, and a comparison was made with three other machine learning models. The experimental results demonstrated the effectiveness of the proposed algorithm in classifying defects on highly reflective metal surfaces such as steel balls. The model achieved a classification accuracy of 97.15%.

show abstract

Classification of Surface Defects on Steel Strip Images using Convolution Neural Network and Support Vector Machine

Cited by 31 publications

References 33 publications

Steel surface defect recognition using classifier combination

Steel surface defect recognition using classifier combination

Deep Learning: Historical Overview from Inception to Actualization, Models, Applications and Future Trends

Research on surface defect identification of steel balls based on improved K-CV parameter optimization support vector machine

Contact Info

Product

Resources

About