scholarly journals Steel Surface Defect Classification Using Deep Residual Neural Network

Metals ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. 846
Author(s):  
Ihor Konovalenko ◽  
Pavlo Maruschak ◽  
Janette Brezinová ◽  
Ján Viňáš ◽  
Jakub Brezina
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Speed ◽  
Steel Surface ◽  
Surface Defect ◽  
Surface Defects ◽  
Defect Classification ◽  
Flat Surfaces ◽  
Automated Method ◽  
Speed And Accuracy

An automated method for detecting and classifying three classes of surface defects in rolled metal has been developed, which allows for conducting defectoscopy with specified parameters of efficiency and speed. The possibility of using the residual neural networks for classifying defects has been investigated. The classifier based on the ResNet50 neural network is accepted as a basis. The model allows classifying images of flat surfaces with damage of three classes with the general accuracy of 96.91% based on the test data. The use of ResNet50 is shown to provide excellent recognition, high speed, and accuracy, which makes it an effective tool for detecting defects on metal surfaces.

scholarly journals Steel Surface Defect Classification Based on Small Sample Learning

2021 ◽  
Vol 11 (23) ◽  
pp. 11459
Author(s):  
Shiqing Wu ◽  
Shiyu Zhao ◽  
Qianqian Zhang ◽  
Long Chen ◽  
Chenrui Wu
Keyword(s):  
Feature Extraction ◽  
Steel Surface ◽  
Surface Defect ◽  
Nearest Neighbor ◽  
Surface Defects ◽  
Feature Space ◽  
Small Sample ◽  
Defect Classification ◽  
Sample Number ◽  
Degradation Problem

The classification of steel surface defects plays a very important role in analyzing their causes to improve manufacturing process and eliminate defects. However, defective samples are very scarce in actual production, so using very few samples to construct a good classifier is a challenge to be addressed. If the layer number of the model with proper depth is increased, the model accuracy will decrease (not caused by overfit), and the training error as well as the test error will be very high. This is called the degradation problem. In this paper, we propose to use feature extraction + feature transformation + nearest neighbors to classify steel surface defects. In order to solve the degradation problem caused by network deepening, the three feature extraction networks of Residual Net, Mobile Net and Dense Net are designed and analyzed. Experiment results show that in the case of a small sample number, Dense block can better solve the degradation problem caused by network deepening than Residual block. Moreover, if Dense Net is used as the feature extraction network, and the nearest neighbor classification algorithm based on Euclidean metric is used in the new feature space, the defect classification accuracy can reach 92.33% when only five labeled images of each category are used as the training set. This paper is of some guiding significance for surface defect classification when the sample number is small.

Recognition and Classification of Hot Strip Surface Defect Based on Binary Tree SVM

2012 ◽  
Vol 538-541 ◽  
pp. 427-430 ◽  
Author(s):  
An Na Wang ◽  
Chao Hu ◽  
Chang Liang Xue ◽  
Hong Rui Zhang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Binary Tree ◽  
Surface Defect ◽  
Surface Defects ◽  
Defect Classification ◽  
Strip Surface ◽  
Hot Strip ◽  
Classification Time

The paper presents a new method which uses Binary Tree SVM in the automatic classification of surface defects for hot strip. Two types of Binary Tree SVMs are applied in defect classification. Compared with BP neural network and one-against-one SVM, the algorithm adopted in the paper greatly improved the accuracy of classification and decreased the classification time.

scholarly journals A Light-Weight Deep-Learning Model with Multi-Scale Features for Steel Surface Defect Classification

Materials ◽  
2020 ◽  
Vol 13 (20) ◽  
pp. 4629
Author(s):  
Yang Liu ◽  
Yachao Yuan ◽  
Cristhian Balta ◽  
Jing Liu
Keyword(s):  
Real Time ◽  
Steel Surface ◽  
Surface Defect ◽  
Surface Defects ◽  
Defect Classification ◽  
Multi Scale ◽  
Training Samples ◽  
Training Cost ◽  
Real Time Applications ◽  
Deep Learning Model

Automatic inspection of surface defects is crucial in industries for real-time applications. Nowadays, computer vision-based approaches have been successfully employed. However, most of the existing works need a large number of training samples to achieve satisfactory classification results, while collecting massive training datasets is labor-intensive and financially costly. Moreover, most of them obtain high accuracy at the expense of high latency, and are thus not suitable for real-time applications. In this work, a novel Concurrent Convolutional Neural Network (ConCNN) with different image scales is proposed, which is light-weighted and easy to deploy for real-time defect classification applications. To evaluate the performance of ConCNN, the NEU-CLS dataset is used in our experiments. Simulation results demonstrate that ConCNN performs better than other state-of-the-art approaches considering accuracy and latency for steel surface defect classification. Specifically, ConCNN achieves as high as 98.89% classification accuracy with only around 5.58 ms latency over low training cost.

scholarly journals Impact of Image Compression on the Performance of Steel Surface Defect Classification with a CNN

2021 ◽  
Vol 10 (4) ◽  
pp. 73
Author(s):  
Tajeddine Benbarrad ◽  
Lamiae Eloutouate ◽  
Mounir Arioua ◽  
Fatiha Elouaai ◽  
My Driss Laanaoui
Keyword(s):  
Machine Vision ◽  
Image Compression ◽  
High Speed ◽  
Steel Surface ◽  
Surface Defect ◽  
Surface Defects ◽  
High Accuracy ◽  
Classification Performance ◽  
Inspection Time ◽  
The Impact

Machine vision is increasingly replacing manual steel surface inspection. The automatic inspection of steel surface defects makes it possible to ensure the quality of products in the steel industry with high accuracy. However, the optimization of inspection time presents a great challenge for the integration of machine vision in high-speed production lines. In this context, compressing the collected images before transmission is essential to save bandwidth and energy, and improve the latency of vision applications. The aim of this paper was to study the impact of quality degradation resulting from image compression on the classification performance of steel surface defects with a CNN. Image compression was applied to the Northeastern University (NEU) surface-defect database with various compression ratios. Three different models were trained and tested with these images to classify surface defects using three different approaches. The obtained results showed that trained and tested models on the same compression qualities maintained approximately the same classification performance for all used compression grades. In addition, the findings clearly indicated that the classification efficiency was affected when the training and test datasets were compressed using different parameters. This impact was more obvious when there was a large difference between these compression parameters, and for models that achieved very high accuracy. Finally, it was found that compression-based data augmentation significantly increased the classification precision to perfect scores (98–100%), and thus improved the generalization of models when tested on different compression qualities. The importance of this work lies in exploiting the obtained results to successfully integrate image compression into machine vision systems, and as appropriately as possible.

scholarly journals Steel Surface Defect Detection Using Convolutional Neural Network

2020 ◽  
Vol 5 (4) ◽  
pp. 203-208
Author(s):  
Yousra KATEB ◽  
Hocine MEGLOULI ◽  
Abdelmalek KHEBLI
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Steel Surface ◽  
Surface Defect ◽  
Surface Defects ◽  
Construction Material ◽  
Surface Inspection ◽  
Surface Defect Detection ◽  
Quality Of Products

Steel is the most important engineering and construction material in the world. It is used in all aspects of our lives. But as every metal is can be defected and then will not be useful by the consumer Steel surface inspection has seen an important attention in relation with industrial quality of products. In addition, it has been studied in different methods based on image classification in the most of time, but these can detect only such kind of defects in very limited conditions such as illumination, obvious contours, contrast and noise...etc. In this paper, we aim to try a new method to detect steel defects this last depend on artificial intelligence and artificial neural networks. We will discuss the automatic detection of steel surface defects using the convolutional neural network, which can classify the images in their specific classes. The steel we are going to use will be well-classified weather the conditions of imaging are not the same, and this is the advantage of the convolutional neural network in our work. The accuracy and the robustness of the results are so satisfying.

Steel Surface Defect Detection Using an Ensemble of Deep Residual Neural Networks

2021 ◽  
pp. 1-8
Author(s):  
Ihor Konovalenko ◽  
Pavlo Maruschak ◽  
Vitaly Brevus
Keyword(s):  
Neural Networks ◽  
Steel Surface ◽  
Production Efficiency ◽  
Surface Defects ◽  
Model Parameters ◽  
Feature Maps ◽  
Defect Diagnostics ◽  
Neuron Activation ◽  
Surface Defect Detection

Abstract Steel defect diagnostics is important for industry task as it is tied to the product quality and production efficiency. The aim of this paper is evaluating the application of residual neural networks for recognition of industrial steel defects of three classes. Developed and investigated models based on deep residual neural networks for the recognition and classification of surface defects of rolled steel. Investigated the influence of various loss functions, optimizers and hyperparameters on the obtained result and selected optimal model parameters. Based on an ensemble of two deep residual neural networks ResNet50 and ResNet152, a classifier was constructed to detect defects of three classes on flat metal surfaces. The proposed technique allows classifying images with high accuracy. The average binary accuracy of classifying the test data is 96.7% for all images (including defect-free ones). The fields of neuron activation in the convolutional layers of the model were investigated. Feature maps formed in the process were found to reflect the position, size and shape of the objects of interest very well. The proposed ensemble model has proven to be robust and able to accurately recognize steel surface defects. Erroneous recognition cases of the classifier application are investigated. It was shown that errors most often occur in ambiguous situations, where surface artifacts of different types are similar.

A fully automated method of human identification based on dental panoramic radiographs using a convolutional neural network

2021 ◽  
Author(s):  
Young Hyun Kim ◽  
Eun-Gyu Ha ◽  
Kug Jin Jeon ◽  
Chena Lee ◽  
Sang-Sun Han
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Speed ◽  
Large Scale ◽  
Oral Surgery ◽  
Human Identification ◽  
Running Time ◽  
Automated Method ◽  
Image Characteristics ◽  
Proposed Model

Objectives: This study aimed to develop a fully automated human identification method based on a convolutional neural network (CNN) with a large-scale dental panoramic radiograph (DPR) dataset. Methods: In total, 2,760 DPRs from 746 subjects who had 2 to 17 DPRs with various changes in image characteristics due to various dental treatments (tooth extraction, oral surgery, prosthetics, orthodontics, or tooth development) were collected. The test dataset included the latest DPR of each subject (746 images) and the other DPRs (2,014 images) were used for model training. A modified VGG16 model with two fully connected layers was applied for human identification. The proposed model was evaluated with rank-1, –3, and −5 accuracies, running time, and gradient-weighted class activation mapping (Grad-CAM)–applied images. Results: This model had rank-1,–3, and −5 accuracies of 82.84%, 89.14%, and 92.23%, respectively. All rank-1 accuracy values of the proposed model were above 80% regardless of changes in image characteristics. The average running time to train the proposed model was 60.9 sec per epoch, and the prediction time for 746 test DPRs was short (3.2 sec/image). The Grad-CAM technique verified that the model automatically identified humans by focusing on identifiable dental information. Conclusion: The proposed model showed good performance in fully automatic human identification despite differing image characteristics of DPRs acquired from the same patients. Our model is expected to assist in the fast and accurate identification by experts by comparing large amounts of images and proposing identification candidates at high speed.

scholarly journals Application of the neural network computing technology for calculating the interval-index characteristics of a minimally redundant modular code

2019 ◽  
Vol 62 (6) ◽  
pp. 652-660
Author(s):  
A. F. Chernyavsky ◽  
A. A. Kolyada ◽  
S. Yu. Protasenya
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Speed ◽  
Theoretical Estimate ◽  
Structural Complexity ◽  
Fold Increase ◽  
Number System ◽  
Parallel Structure ◽  
Network Computing ◽  
Time Expenditures

The article is devoted to the problem of creation of high-speed neural networks (NN) for calculation of interval-index characteristics of a minimally redundant modular code. The functional base of the proposed solution is an advanced class of neural networks of a final ring. These neural networks perform position-modular code transformations of scalable numbers using a modified reduction technology. A developed neural network has a uniform parallel structure, easy to implement and requires the time expenditures of the order (3[log2b]+ [log2k]+6tsum  close to the lower theoretical estimate. Here b and k is the average bit capacity and the number of modules respectively; t sum is the duration of the two-place operation of adding integers. The refusal from a normalization of the numbers of the modular code leads to a reduction of the required set of NN of the finite ring on the (k – 1) component. At the same time, the abnormal configuration of minimally redundant modular coding requires an average k-fold increase in the interval index module (relative to the rest of the bases of the modular number system). It leads to an adequate increase in hardware expenses on this module. Besides, the transition from normalized to unregulated coding reduces the level of homogeneity of the structure of the NN for calculating intervalindex characteristics. The possibility of reducing the structural complexity of the proposed NN by using abnormal intervalindex characteristics is investigated.

scholarly journals Deep Learning Framework for Steel Surface Defects Classification

2019 ◽  
Vol 4 (1) ◽  
pp. 25-32
Author(s):  
Ranganath Singari ◽  
Karun Singla ◽  
Gangesh Chawla
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Architecture ◽  
Steel Surface ◽  
Surface Defects ◽  
Fixed Number ◽  
Quality Level ◽  
Acceptance Sampling ◽  
Quality Inspection ◽  
Defects Classification

Deep learning has offered new avenues in the field of industrial management. Traditional methods of quality inspection such as Acceptance Sampling relies on a probabilistic measure derived from inspecting a sample of finished products. Evaluating a fixed number of products to derive the quality level for the complete batch is not a robust approach. Visual inspection solutions based on deep learning can be employed in the large manufacturing units to improve the quality inspection units for steel surface defect detection. This leads to optimization of the human capital due to reduction in manual intervention and turnaround time in the overall supply chain of the industry. Consequently, the sample size in the Acceptance sampling can be increased with minimal effort vis-à-vis an increase in the overall accuracy of the inspection. The learning curve of this work is supported by Convolutional Neural Network which has been used to extract feature representations from grayscale images to classify theinputs into six types of surface defects. The neural network architecture is compiled in Keras framework using Tensorflow backend with state of the art Adam RMS Prop with Nesterov Momentum (NADAM) optimizer. The proposed classification algorithm holds the potential to identify the dominant flaws in the manufacturing system responsible for leaking costs.

Sign in / Sign up

Export Citation Format

Share Document