Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks
Automatic detection of steel surface defects is very important for product quality control in the steel industry. However, the traditional method cannot be well applied in the production line, because of its low accuracy and slow running speed. The current, popular algorithm (based on deep learning)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/11/3/388 |
| _version_ | 1797395062105047040 |
|---|---|
| author | Shuai Wang Xiaojun Xia Lanqing Ye Binbin Yang |
| author_facet | Shuai Wang Xiaojun Xia Lanqing Ye Binbin Yang |
| author_sort | Shuai Wang |
| collection | DOAJ |
| description | Automatic detection of steel surface defects is very important for product quality control in the steel industry. However, the traditional method cannot be well applied in the production line, because of its low accuracy and slow running speed. The current, popular algorithm (based on deep learning) also has the problem of low accuracy, and there is still a lot of room for improvement. This paper proposes a method combining improved ResNet50 and enhanced faster region convolutional neural networks (faster R-CNN) to reduce the average running time and improve the accuracy. Firstly, the image input into the improved ResNet50 model, which add the deformable revolution network (DCN) and improved cutout to classify the sample with defects and without defects. If the probability of having a defect is less than 0.3, the algorithm directly outputs the sample without defects. Otherwise, the samples are further input into the improved faster R-CNN, which adds spatial pyramid pooling (SPP), enhanced feature pyramid networks (FPN), and matrix NMS. The final output is the location and classification of the defect in the sample or without defect in the sample. By analyzing the data set obtained in the real factory environment, the accuracy of this method can reach 98.2%. At the same time, the average running time is faster than other models. |
| first_indexed | 2024-03-09T00:28:57Z |
| format | Article |
| id | doaj.art-f76b18b4c2f94c188615e35e345a317e |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-09T00:28:57Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-f76b18b4c2f94c188615e35e345a317e2023-12-11T18:40:32ZengMDPI AGMetals2075-47012021-02-0111338810.3390/met11030388Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural NetworksShuai Wang0Xiaojun Xia1Lanqing Ye2Binbin Yang3School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, ChinaSchool of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, ChinaSchool of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, ChinaSchool of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, ChinaAutomatic detection of steel surface defects is very important for product quality control in the steel industry. However, the traditional method cannot be well applied in the production line, because of its low accuracy and slow running speed. The current, popular algorithm (based on deep learning) also has the problem of low accuracy, and there is still a lot of room for improvement. This paper proposes a method combining improved ResNet50 and enhanced faster region convolutional neural networks (faster R-CNN) to reduce the average running time and improve the accuracy. Firstly, the image input into the improved ResNet50 model, which add the deformable revolution network (DCN) and improved cutout to classify the sample with defects and without defects. If the probability of having a defect is less than 0.3, the algorithm directly outputs the sample without defects. Otherwise, the samples are further input into the improved faster R-CNN, which adds spatial pyramid pooling (SPP), enhanced feature pyramid networks (FPN), and matrix NMS. The final output is the location and classification of the defect in the sample or without defect in the sample. By analyzing the data set obtained in the real factory environment, the accuracy of this method can reach 98.2%. At the same time, the average running time is faster than other models.https://www.mdpi.com/2075-4701/11/3/388steel surface defect detectionimproved ResNet50improved faster R-CNNspatial pyramid pooling (SPP)feature pyramid networks (FPN) |
| spellingShingle | Shuai Wang Xiaojun Xia Lanqing Ye Binbin Yang Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks Metals steel surface defect detection improved ResNet50 improved faster R-CNN spatial pyramid pooling (SPP) feature pyramid networks (FPN) |
| title | Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks |
| title_full | Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks |
| title_fullStr | Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks |
| title_full_unstemmed | Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks |
| title_short | Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks |
| title_sort | automatic detection and classification of steel surface defect using deep convolutional neural networks |
| topic | steel surface defect detection improved ResNet50 improved faster R-CNN spatial pyramid pooling (SPP) feature pyramid networks (FPN) |
| url | https://www.mdpi.com/2075-4701/11/3/388 |
| work_keys_str_mv | AT shuaiwang automaticdetectionandclassificationofsteelsurfacedefectusingdeepconvolutionalneuralnetworks AT xiaojunxia automaticdetectionandclassificationofsteelsurfacedefectusingdeepconvolutionalneuralnetworks AT lanqingye automaticdetectionandclassificationofsteelsurfacedefectusingdeepconvolutionalneuralnetworks AT binbinyang automaticdetectionandclassificationofsteelsurfacedefectusingdeepconvolutionalneuralnetworks |