scholarly journals Automated Surface Defect Inspection Based on Autoencoders and Fully Convolutional Neural Networks

2021 ◽  
Vol 11 (17) ◽  
pp. 7838
Author(s):  
Cheng-Wei Lei ◽  
Li Zhang ◽  
Tsung-Ming Tai ◽  
Chen-Chieh Tsai ◽  
Wen-Jyi Hwang ◽  
...  
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Training Data ◽  
Defect Inspection ◽  
Fully Convolutional Neural Networks ◽  
High Flexibility ◽  
Vision Algorithm ◽  
Online Inspection ◽  
Smart Factories ◽  
Quality Production

This study aims to develop a novel automated computer vision algorithm for quality inspection of surfaces with complex patterns. The proposed algorithm is based on both an autoencoder (AE) and a fully convolutional neural network (FCN). The AE is adopted for the self-generation of templates from test targets for defect detection. Because the templates are produced from the test targets, the position alignment issues for the matching operations between templates and test targets can be alleviated. The FCN is employed for the segmentation of a template into a number of coherent regions. Because the AE has the limitation that its capacities for the regeneration of each coherent region in the template may be different, the segmentation of the template by FCN is beneficial for allowing the inspection of each region to be independently carried out. In this way, more accurate detection results can be achieved. Experimental results reveal that the proposed algorithm has the advantages of simplicity for training data collection, high accuracy for defect detection, and high flexibility for online inspection. The proposed algorithm is therefore an effective alternative for the automated inspection in smart factories with a growing demand for the reliability for high quality production.

scholarly journals PSIC-Net: Pixel-Wise Segmentation and Image-Wise Classification Network for Surface Defects

Machines ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 221
Author(s):  
Linjian Lei ◽  
Shengli Sun ◽  
Yue Zhang ◽  
Huikai Liu ◽  
Wenjun Xu
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Surface Defect ◽  
Performance Metrics ◽  
Surface Defects ◽  
Training Data ◽  
Detection Methods ◽  
Detection Technology ◽  
Surface Defect Detection ◽  
Public Datasets

Recent years have witnessed the widespread research of the surface defect detection technology based on machine vision, which has spawned various effective detection methods. In particular, the rise of deep learning has allowed the surface defect detection technology to develop further. However, these methods based on deep learning still have some drawbacks. For example, the size of the sample data is not large enough to support deep learning; the location and recognition of surface defects are not accurate enough; the real-time performance of segmentation and classification is not satisfactory. In the context, this paper proposes an end-to-end convolutional neural network model: the pixel-wise segmentation and image-wise classification network (PSIC-Net). With the innovative design of a three-stage network structure, improved loss function and a two-step training mode, PSIC-Net can accurately and quickly segment and classify surface defects with a small dataset of training data. This model was evaluated with three public datasets, and compared with the most advanced defect detection methods. All the performance metrics prove the effectiveness and advancement of PSIC-Net.

scholarly journals Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1562 ◽  
Author(s):  
Xiaoming Lv ◽  
Fajie Duan ◽  
Jia-jia Jiang ◽  
Xiao Fu ◽  
Lin Gan
Keyword(s):  
Defect Detection ◽  
Large Scale ◽  
Surface Defect ◽  
Data Augmentation ◽  
Training Data ◽  
Metallic Surface ◽  
Single Shot ◽  
Limited Data ◽  
Detection Model ◽  
Surface Defect Detection

Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. However, due to the limited data scale and defect categories, existing defect datasets are generally unavailable for the deployment of the detection model. To address this problem, we contribute a new dataset called GC10-DET for large-scale metallic surface defect detection. The GC10-DET dataset has great challenges on defect categories, image number, and data scale. Besides, traditional detection approaches are poor in both efficiency and accuracy for the complex real-world environment. Thus, we also propose a novel end-to-end defect detection network (EDDN) based on the Single Shot MultiBox Detector. The EDDN model can deal with defects with different scales. Furthermore, a hard negative mining method is designed to alleviate the problem of data imbalance, while some data augmentation methods are adopted to enrich the training data for the expensive data collection problem. Finally, the extensive experiments on two datasets demonstrate that the proposed method is robust and can meet accuracy requirements for metallic defect detection.

scholarly journals Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks

2018 ◽  
Vol 8 (9) ◽  
pp. 1575 ◽  
Author(s):  
Xian Tao ◽  
Dapeng Zhang ◽  
Wenzhi Ma ◽  
Xilong Liu ◽  
De Xu
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Semantic Segmentation ◽  
Low Noise ◽  
Machine Learning Techniques ◽  
Metallic Surface ◽  
Defect Inspection ◽  
Learning Techniques ◽  
Defect Image ◽  
Surface Defect Detection

Automatic metallic surface defect inspection has received increased attention in relation to the quality control of industrial products. Metallic defect detection is usually performed against complex industrial scenarios, presenting an interesting but challenging problem. Traditional methods are based on image processing or shallow machine learning techniques, but these can only detect defects under specific detection conditions, such as obvious defect contours with strong contrast and low noise, at certain scales, or under specific illumination conditions. This paper discusses the automatic detection of metallic defects with a twofold procedure that accurately localizes and classifies defects appearing in input images captured from real industrial environments. A novel cascaded autoencoder (CASAE) architecture is designed for segmenting and localizing defects. The cascading network transforms the input defect image into a pixel-wise prediction mask based on semantic segmentation. The defect regions of segmented results are classified into their specific classes via a compact convolutional neural network (CNN). Metallic defects under various conditions can be successfully detected using an industrial dataset. The experimental results demonstrate that this method meets the robustness and accuracy requirements for metallic defect detection. Meanwhile, it can also be extended to other detection applications.

Web Surface Defect Segmentation Based on Stationary Wavelet Transform

2012 ◽  
Vol 433-440 ◽  
pp. 426-431 ◽  
Author(s):  
Zheng Wang
Keyword(s):  
Spectral Analysis ◽  
Wavelet Transform ◽  
Image Fusion ◽  
Defect Detection ◽  
High Performance ◽  
Surface Defect ◽  
Defect Inspection ◽  
Stationary Wavelet Transform ◽  
Novel Approach ◽  
Gray Level Image

Typical characteristics of web manufacturing process ,when compared with other sheet or flat product manufacturing, are the large value of web width and production speed .So the development of new and efficient algorithm invokes the interests of many researchers. This paper describes a novel approach based on stationary wavelet transform for the segmentation of web surface defect. The segmentation is performed firstly by decomposing the gray level image into sub-band images and then by an image fusion scheme for the sub-images. Compared with orthogonal wavelet transform (OWT), the notable advantage of stationary wavelet transform (SWT) is its shift invariance. These properties are especially important for defect detection. Image fusion makes full use of available information in each sub-band images to obtain better output results when compared with ordinary image enhancement. Experimental results demonstrate the validity of our method. The proposed method is targeted for web surface defect inspection but has the potential for broader application areas such as steel, wood and fabric defect detection. With the development of high performance signal processors, spectral analysis or a combination of statistical and spectral analysis would be the trend of web surface defect inspection.

Rapid Failure Analysis of Low-Yielding Electrical Test Structures Using E-beam Physical and Voltage Contrast Inspection

2013 ◽  
Author(s):  
Oliver D. Patterson ◽  
Deborah A. Ryan ◽  
Xiaohu Tang ◽  
Shuen Cheng Lei
Keyword(s):  
Failure Analysis ◽  
Defect Detection ◽  
High Volume ◽  
The Other ◽  
Defect Inspection ◽  
Electrical Test ◽  
Detection Mode ◽  
Rapid Generation ◽  
Voltage Contrast ◽  
Additional Support

Abstract In-line E-beam inspection may be used for rapid generation of failure analysis (FA) results for low yielding test structures. This approach provides a number of advantages: 1) It is much earlier than traditional FA, 2) de-processing isn’t required, and 3) a high volume of sites can be processed with the additional support of an in-line FIB. Both physical defect detection and voltage contrast inspection modes are useful for this application. Voltage contrast mode is necessary for isolation of buried defects and is the preferred approach for opens, because it is faster. Physical defect detection mode is generally necessary to locate shorts. The considerations in applying these inspection modes for rapid failure analysis are discussed in the context of two examples: one that lends itself to physical defect inspection and the other, more appropriately addressed with voltage contrast inspection.

SDDNet: A Fast and Accurate Network for Surface Defect Detection

2021 ◽  
Vol 70 ◽  
pp. 1-13
Author(s):  
Lisha Cui ◽  
Xiaoheng Jiang ◽  
Mingliang Xu ◽  
Wanqing Li ◽  
Pei Lv ◽  
...  
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Surface Defect Detection
Sign in / Sign up

Export Citation Format

Share Document