Automated defect inspection system for metal surfaces based on deep learning and data augmentation

Yun, Jong Pil; Shin, WooSang; Koo, Gyogwon; Kim, Min Su; Lee, Chungki; Lee, Sang Jun

doi:10.1016/j.jmsy.2020.03.009

Cited by 172 publications

(68 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to achieve satisfactory results with a small number of training samples, data augmentation as well as transfer learning are the key ingredients for training networks. For instance, Yun et al [ 120 ] used the conditional convolutional variational autoencoder (CCVAE) as the data augmentation method, and various defect images are generated by learning the distribution of the given defect data using CCVAE. The experiments showed that in the case of data augmentation using CCVAE, the accuracy could increase from 96.27% to 99.69%, and the F-measure also increased from 96.27% to 99.71%.…”

Section: Taxonomy Of Two-dimension Defect Detection Methodsmentioning

confidence: 99%

Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials

Fang

Luo

Zhou

et al. 2020

Sensors

View full text Add to dashboard Cite

The computer-vision-based surface defect detection of metal planar materials is a research hotspot in the field of metallurgical industry. The high standard of planar surface quality in the metal manufacturing industry requires that the performance of an automated visual inspection system and its algorithms are constantly improved. This paper attempts to present a comprehensive survey on both two-dimensional and three-dimensional surface defect detection technologies based on reviewing over 160 publications for some typical metal planar material products of steel, aluminum, copper plates and strips. According to the algorithm properties as well as the image features, the existing two-dimensional methodologies are categorized into four groups: statistical, spectral, model, and machine learning-based methods. On the basis of three-dimensional data acquisition, the three-dimensional technologies are divided into stereoscopic vision, photometric stereo, laser scanner, and structured light measurement methods. These classical algorithms and emerging methods are introduced, analyzed, and compared in this review. Finally, the remaining challenges and future research trends of visual defect detection are discussed and forecasted at an abstract level.

show abstract

Section: Taxonomy Of Two-dimension Defect Detection Methodsmentioning

confidence: 99%

Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials

Fang

Luo

Zhou

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…This classifier was trained by images collected from both actual production lines and randomly created by the GAN, which cleverly solved the engineering problem of sample limitation and improved the generalization ability of the classifiers effectively. In addition to GAN, Yun et al [136] also proposed a modern Convolutional Variational Autoencoder (CVAE) and deep CNN-based defect classification algorithm to address the insufficient of imbalanced data. The experimental results demonstrates the excellent performance of image generation and defect inspection of the presented methods.…”

Section: Semisupervised Learningmentioning

confidence: 99%

Automated Visual Defect Classification for Flat Steel Surface: A Survey

Luo

Fang

et al. 2020

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

For a typical surface automated visual inspection (AVI) instrument of planar materials, defect classification is an indispensable part after defect detection, which acts as a crucial precondition for achieving the on-line quality inspection of end products. In the industrial environment of manufacturing flat steels, this task is awfully difficult due to diverse defect appearances, ambiguous intraclass and interclass distances. This paper attempts to present a focused but systematic review of the traditional and emerging automated computer-vision-based defect classification methods by investigating approximately 140 studies on three specific flat steel products of con-casting slabs, hot-rolled steel strips and cold-rolled steel strips. According to the natural image processing procedure of defect recognition, the diverse approaches are grouped into five successive parts: image acquisition, image preprocessing, feature extraction, feature selection and defect classifier. Recent literature has been reviewed from an industrial goal-oriented perspective to provide some guidelines for future studies, as well as to recommend suitable methods for boosting the surface quality inspection level of AVI instruments.

show abstract

“…The condition of the rolled surface is monitored using the automated optical-digital control systems, which make it possible to identify defects in real time, as well as recognize and classify them [6,7]. Such systems are based on a previous study of defect groups using materials from databases, technological and morphological analysis [8]. In previous articles, the types and causes of the main defects are analyzed, and their characteristics are described [9].…”

Section: Introductionmentioning

confidence: 99%

Recognition of Scratches and Abrasions on Metal Surfaces Using a Classifier Based on a Convolutional Neural Network

Konovalenko

Maruschak

Brevus³

et al. 2021

Metals

View full text Add to dashboard Cite

Classification of steel surface defects in steel industry is essential for their detection and also fundamental for the analysis of causes that lead to damages. Timely detection of defects allows to reduce the frequency of their appearance in the final product. This paper considers the classifiers for the recognition of scratches, scrapes and abrasions on metal surfaces. Classifiers are based on the ResNet50 and ResNet152 deep residual neural network architecture. The proposed technique supports the recognition of defects in images and does this with high accuracy. The binary accuracy of the classification based on the test data is 97.14%. The influence of a number of training conditions on the accuracy metrics of the model have been studied. The augmentation conditions have been figured out to make the greatest contribution to improving the accuracy during training. The peculiarities of damages that cause difficulties in their recognition have been studied. The fields of neuron activation have been investigated in the convolutional layers of the model. Feature maps which developed in this case have been found to correspond to the location of the objects of interest. Erroneous cases of the classifier application have been considered. The peculiarities of damages that cause difficulties in their recognition have been studied.

show abstract

Automated defect inspection system for metal surfaces based on deep learning and data augmentation

Cited by 172 publications

References 23 publications

Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials

Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials

Automated Visual Defect Classification for Flat Steel Surface: A Survey

Recognition of Scratches and Abrasions on Metal Surfaces Using a Classifier Based on a Convolutional Neural Network

Contact Info

Product

Resources

About