The Experts below are selected from a list of 128781 Experts worldwide ranked by ideXlab platform
Mingming Jiang - One of the best experts on this subject based on the ideXlab platform.
-
an end to end steel strip Surface Defects recognition system based on convolutional neural networks
Steel Research International, 2017Co-Authors: Mingming JiangAbstract:Steel strip Surface Defects recognition is very important to steel strip production and quality control, which needs further improvement. In this paper, an end-to-end Surface Defects recognition system is proposed for steel strip Surface inspection. This system is based on the symmetric surround saliency map for Surface Defects detection and deep convolutional neural networks (CNNs) which directly use the defect image as input and defect category as output for seven classes of steel strip Defects classification. The CNNs are trained purely on raw defect images and learned defect features from the training of network, which avoiding the separation between feature extraction and image classification, so that forms an end-to-end Defects recognition pipeline. To further illustrate the superiority of the defect recognition methods with CNNs, an authoritative and standard steel strip Surface defect dataset − NEU is also used to evaluate the defect recognition effect using CNNs. Experimental results demonstrate that the proposed methods perform well in steel strip Surface defect detection of different types and achieve a high recognition rate for defect images. In addition, a series of data augmentation methods are discussed to analyze its effect on avoiding over-fitting for Defects recognition.
-
An End‐to‐End Steel Strip Surface Defects Recognition System Based on Convolutional Neural Networks
Steel Research International, 2016Co-Authors: Li Yi, Guangyao Li, Mingming JiangAbstract:Steel strip Surface Defects recognition is very important to steel strip production and quality control, which needs further improvement. In this paper, an end-to-end Surface Defects recognition system is proposed for steel strip Surface inspection. This system is based on the symmetric surround saliency map for Surface Defects detection and deep convolutional neural networks (CNNs) which directly use the defect image as input and defect category as output for seven classes of steel strip Defects classification. The CNNs are trained purely on raw defect images and learned defect features from the training of network, which avoiding the separation between feature extraction and image classification, so that forms an end-to-end Defects recognition pipeline. To further illustrate the superiority of the defect recognition methods with CNNs, an authoritative and standard steel strip Surface defect dataset − NEU is also used to evaluate the defect recognition effect using CNNs. Experimental results demonstrate that the proposed methods perform well in steel strip Surface defect detection of different types and achieve a high recognition rate for defect images. In addition, a series of data augmentation methods are discussed to analyze its effect on avoiding over-fitting for Defects recognition.
Davide Gaiotto - One of the best experts on this subject based on the ideXlab platform.
-
Surface Defects and Chiral Algebras
Journal of High Energy Physics, 2017Co-Authors: Clay Cordova, Davide Gaiotto, Shu-heng ShaoAbstract:We investigate superconformal Surface Defects in four-dimensional $$ \mathcal{N}=2 $$ superconformal theories. Each such defect gives rise to a module of the associated chiral algebra and the Surface defect Schur index is the character of this module. Various natural chiral algebra operations such as Drinfeld-Sokolov reduction and spectral flow can be interpreted as constructions involving four-dimensional Surface Defects. We compute the index of these Defects in the free hypermultiplet theory and Argyres-Douglas theories, using both infrared techniques involving BPS states, as well as renormalization group flows onto Higgs branches. In each case we find perfect agreement with the predicted characters.
-
Surface Defects and resolvents
Journal of High Energy Physics, 2013Co-Authors: Davide Gaiotto, Sergei Gukov, Nathan SeibergAbstract:We study a large class of BPS Surface Defects in 4d N=2 gauge theories. They are defined by coupling a 2d N=(2,2) gauged linear sigma model to the 4d bulk degrees of freedom. Our main result is an efficient computation of the effective twisted superpotential for all these models in terms of a basic object closely related to the resolvent of the 4d gauge theory, which encodes the curve describing the 4d low energy dynamics. We reproduce and extend the results of brane constructions and compute the effective twisted superpotential for general monodromy Surface Defects. We encounter novel, puzzling field theory phenomena in the low energy dynamics of the simplest Surface Defects and we propose some local models to explain them. We also study in some detail the behavior of Surface Defects near monopole points of the bulk theory’s Coulomb branch. Finally, we explore the effect on the defect of breaking the bulk supersymmetry from N=2 to N=1 and show that certain quantities are independent of this breaking.
-
Bootstrapping the superconformal index with Surface Defects
Journal of High Energy Physics, 2013Co-Authors: Davide Gaiotto, Leonardo Rastelli, Shlomo S. RazamatAbstract:The analytic properties of theN = 2 superconformal index are given a physical interpretation in terms of certain BPS Surface Defects, which arise as the IR limit of supersymmetric vortices. The residue of the index at a pole in avor fugacity is interpreted as the index of a superconformal eld theory without this avor symmetry, but endowed with an additional Surface defect. The residue can be eciently extracted by acting on the index with a difference operator of Ruijsenaars-Schneider type. By imposing the associativity constraints of S-duality, we are then able to evaluate the index of all generalized quiver theories of type A, for generic values of the three superconformal fugacities, with or without Surface Defects.
Ruofeng Wei - One of the best experts on this subject based on the ideXlab platform.
-
Research on Recognition Technology of Aluminum Profile Surface Defects Based on Deep Learning.
Materials, 2019Co-Authors: Ruofeng WeiAbstract:Aluminum profile Surface Defects can greatly affect the performance, safety, and reliability of products. Traditional human-based visual inspection has low accuracy and is time consuming, and machine vision-based methods depend on hand-crafted features that need to be carefully designed and lack robustness. To recognize the multiple types of Defects with various size on aluminum profiles, a multiscale defect-detection network based on deep learning is proposed. Then, the network is trained and evaluated using aluminum profile Surface Defects images. Results show 84.6%, 48.5%, 96.9%, 97.9%, 96.9%, 42.5%, 47.2%, 100%, 100%, and 43.3% average precision (AP) for the 10 defect categories, respectively, with a mean AP of 75.8%, which illustrate the effectiveness of the network in aluminum profile Surface Defects detection. In addition, saliency maps also show the feasibility of the proposed network.
-
Research on Recognition Technology of Aluminum Profile Surface Defects Based on Deep Learning
2019Co-Authors: Ruofeng WeiAbstract:Aluminum profile Surface Defects can greatly affect the performance, safety and reliability of products. Traditional human-based visual inspection is low accuracy and time consuming, and machine vision-based methods depend on hand-crafted features which need to be carefully designed and lack robustness. To recognize the multiple types of Defects with various size on aluminum profiles, a multiscale defect detection network based on deep learning is proposed. Then, the network is trained and evaluated using aluminum profile Surface Defects images. Results show 84.6%, 48.5%, 96.9%, 97.9%, 96.9%, 42.5%, 47.2%, 100%, 100%, 43.3% average precision(AP) for the ten defect categories, respectively, with a mean AP of 75.8%, which illustrate the effectiveness of the network in aluminum profile Surface Defects detection. In addition, saliency maps also show the feasibility of the proposed network.
Jiangyun Li - One of the best experts on this subject based on the ideXlab platform.
-
Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network
IFAC-PapersOnLine, 2018Co-Authors: Jiangyun Li, Zhenfeng Su, Jiahui GengAbstract:Abstract The Surface Defects of steel strip have diverse and complex features, and Surface Defects caused by different production lines tend to have different characteristics. Therefore, the detection algorithms for the Surface Defects of steel strip should have good generalization performance. Aiming at detecting Surface Defects of steel strip, we established a dataset of six types of Surface Defects on cold-rolled steel strip and augmented it in order to reduce over-fitting. We improved the You Only Look Once (YOLO) network and made it all convolutional. Our improved network, which consists of 27 convolution layers, provides an end-to-end solution for the Surface Defects detection of steel strip. We evaluated the six types of Defects with our network and reached performance of 97.55% mAP and 95.86% recall rate. Besides, our network achieves 99% detection rate with speed of 83 FPS, which provides methodological support for real-time Surface Defects detection of steel strip. It can also predict the location and size information of defect regions, which is of great significance for evaluating the quality of an entire steel strip production line.
-
Real-Time Classification of Steel Strip Surface Defects Based on Deep CNNs
Proceedings of 2018 Chinese Intelligent Systems Conference, 2018Co-Authors: Jiahui Geng, Zhenfeng Su, Weicun Zhang, Jiangyun LiAbstract:Steel strip Surface Defects recognition is very important to steel strip production and quality control, in which correct classification of these Surface Defects is crucial. The Surface Defects of steel strips are classified according to various features, but it is hard for traditional methods to extract all these features and use them effectively. In this paper, we propose a method to deal with the problem of defect classification based on deep convolutional neural networks (CNNs). We adopt GoogLeNet, as our base model and add an identity mapping to it, which obtains improvement to some extent. At the same time, we establish a dataset of cold-rolled steel strip Surface Defects of six types and augment it in order to reduce over-fitting. Then we detect Defects of six types with our network and reach an accuracy of 98.57%. Besides, our network achieves a speed of 125 FPS, which fully meets the real-time requirement of the actual steel strip production lines.
Jiahui Geng - One of the best experts on this subject based on the ideXlab platform.
-
Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network
IFAC-PapersOnLine, 2018Co-Authors: Jiangyun Li, Zhenfeng Su, Jiahui GengAbstract:Abstract The Surface Defects of steel strip have diverse and complex features, and Surface Defects caused by different production lines tend to have different characteristics. Therefore, the detection algorithms for the Surface Defects of steel strip should have good generalization performance. Aiming at detecting Surface Defects of steel strip, we established a dataset of six types of Surface Defects on cold-rolled steel strip and augmented it in order to reduce over-fitting. We improved the You Only Look Once (YOLO) network and made it all convolutional. Our improved network, which consists of 27 convolution layers, provides an end-to-end solution for the Surface Defects detection of steel strip. We evaluated the six types of Defects with our network and reached performance of 97.55% mAP and 95.86% recall rate. Besides, our network achieves 99% detection rate with speed of 83 FPS, which provides methodological support for real-time Surface Defects detection of steel strip. It can also predict the location and size information of defect regions, which is of great significance for evaluating the quality of an entire steel strip production line.
-
Real-Time Classification of Steel Strip Surface Defects Based on Deep CNNs
Proceedings of 2018 Chinese Intelligent Systems Conference, 2018Co-Authors: Jiahui Geng, Zhenfeng Su, Weicun Zhang, Jiangyun LiAbstract:Steel strip Surface Defects recognition is very important to steel strip production and quality control, in which correct classification of these Surface Defects is crucial. The Surface Defects of steel strips are classified according to various features, but it is hard for traditional methods to extract all these features and use them effectively. In this paper, we propose a method to deal with the problem of defect classification based on deep convolutional neural networks (CNNs). We adopt GoogLeNet, as our base model and add an identity mapping to it, which obtains improvement to some extent. At the same time, we establish a dataset of cold-rolled steel strip Surface Defects of six types and augment it in order to reduce over-fitting. Then we detect Defects of six types with our network and reach an accuracy of 98.57%. Besides, our network achieves a speed of 125 FPS, which fully meets the real-time requirement of the actual steel strip production lines.
