scholarly journals A Study of Defect Detection Techniques for Metallographic Images

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5593 ◽  
Author(s):  
Wei-Hung Wu ◽  
Jen-Chun Lee ◽  
Yi-Ming Wang
Keyword(s):  
Neural Network ◽  
Defect Detection ◽  
Network Architecture ◽  
Recognition Performance ◽  
Metallographic Analysis ◽  
Automatic Identification ◽  
Detection Techniques ◽  
Multi Scale ◽  
Modified Method ◽  
Metallographic Images

Metallography is the study of the structure of metals and alloys. Metallographic analysis can be regarded as a detection tool to assist in identifying a metal or alloy, to evaluate whether an alloy is processed correctly, to inspect multiple phases within a material, to locate and characterize imperfections such as voids or impurities, or to find the damaged areas of metallographic images. However, the defect detection of metallography is evaluated by human experts, and its automatic identification is still a challenge in almost every real solution. Deep learning has been applied to different problems in computer vision since the proposal of AlexNet in 2012. In this study, we propose a novel convolutional neural network architecture for metallographic analysis based on a modified residual neural network (ResNet). Multi-scale ResNet (M-ResNet), the modified method, improves efficiency by utilizing multi-scale operations for the accurate detection of objects of various sizes, especially small objects. The experimental results show that the proposed method yields an accuracy of 85.7% (mAP) in recognition performance, which is higher than existing methods. As a consequence, we propose a novel system for automatic defect detection as an application for metallographic analysis.

scholarly journals Image processing of Casting defects based on Convolutional neural network

2021 ◽  
Vol 2137 (1) ◽  
pp. 012059
Author(s):  
Bowen Wei ◽  
Weixin Gao
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Convolutional Neural Network ◽  
Defect Detection ◽  
Network Architecture ◽  
Casting Defect ◽  
Neural Network Architecture ◽  
Vision Inspection ◽  
Design Requirements ◽  
Metal Castings

Abstract At present, there are numerous losses caused by corrosion cracking of metal castings in engineering in China. In order to detect the possible defects of metal castings in engineering, the laser ultrasonic vision inspection technology is used to image the castings, and then the identification efficiency is low. In order to process these images efficiently and quickly, convolutional neural network image processing technology is introduced. According to the actual needs, a convolutional neural network architecture is designed to recognize images, and whether the architecture meets the requirements is verified. Experimental results show that the performance of the architecture meets the design requirements. Under the same conditions, this structure provides a solution for casting defect detection combined with artificial intelligence.

scholarly journals PCEDNet: A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds

2022 ◽  
Vol 41 (1) ◽  
pp. 1-21
Author(s):  
Chems-Eddine Himeur ◽  
Thibault Lejemble ◽  
Thomas Pellegrini ◽  
Mathias Paulin ◽  
Loic Barthe ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Point Clouds ◽  
Scale Space ◽  
Neural Network Architecture ◽  
Multi Scale ◽  
3D Point Clouds ◽  
Space Matrix ◽  
Processing Point

In recent years, Convolutional Neural Networks (CNN) have proven to be efficient analysis tools for processing point clouds, e.g., for reconstruction, segmentation, and classification. In this article, we focus on the classification of edges in point clouds, where both edges and their surrounding are described. We propose a new parameterization adding to each point a set of differential information on its surrounding shape reconstructed at different scales. These parameters, stored in a Scale-Space Matrix (SSM) , provide a well-suited information from which an adequate neural network can learn the description of edges and use it to efficiently detect them in acquired point clouds. After successfully applying a multi-scale CNN on SSMs for the efficient classification of edges and their neighborhood, we propose a new lightweight neural network architecture outperforming the CNN in learning time, processing time, and classification capabilities. Our architecture is compact, requires small learning sets, is very fast to train, and classifies millions of points in seconds.

scholarly journals Ship Identification and Characterization in Sentinel-1 SAR Images with Multi-Task Deep Learning

2019 ◽  
Vol 11 (24) ◽  
pp. 2997 ◽  
Author(s):  
Clément Dechesne ◽  
Sébastien Lefèvre ◽  
Rodolphe Vadaine ◽  
Guillaume Hajduch ◽  
Ronan Fablet
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Architecture ◽  
Large Scale ◽  
Visual Analysis ◽  
Automatic Identification ◽  
Identification System ◽  
Human Observer ◽  
Convolutional Network ◽  
Ship Detection

The monitoring and surveillance of maritime activities are critical issues in both military and civilian fields, including among others fisheries’ monitoring, maritime traffic surveillance, coastal and at-sea safety operations, and tactical situations. In operational contexts, ship detection and identification is traditionally performed by a human observer who identifies all kinds of ships from a visual analysis of remotely sensed images. Such a task is very time consuming and cannot be conducted at a very large scale, while Sentinel-1 SAR data now provide a regular and worldwide coverage. Meanwhile, with the emergence of GPUs, deep learning methods are now established as state-of-the-art solutions for computer vision, replacing human intervention in many contexts. They have been shown to be adapted for ship detection, most often with very high resolution SAR or optical imagery. In this paper, we go one step further and investigate a deep neural network for the joint classification and characterization of ships from SAR Sentinel-1 data. We benefit from the synergies between AIS (Automatic Identification System) and Sentinel-1 data to build significant training datasets. We design a multi-task neural network architecture composed of one joint convolutional network connected to three task specific networks, namely for ship detection, classification, and length estimation. The experimental assessment shows that our network provides promising results, with accurate classification and length performance (classification overall accuracy: 97.25%, mean length error: 4.65 m ± 8.55 m).

scholarly journals MSRCall: A Multi-scale Deep Neural Network to Basecall Oxford Nanopore Sequences

2021 ◽  
Author(s):  
Yang-Ming Yeh ◽  
Yi-Chang Lu
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Ionic Current ◽  
Scale Structure ◽  
Neural Network Architecture ◽  
Translation Process ◽  
Multi Scale ◽  
Oxford Nanopore ◽  
Rna Fragments ◽  
Oxford Nanopore Technologies

MinION, a third-generation sequencer from Oxford Nanopore Technologies, is a portable device that can provide long nucleotide read data in real-time. It primarily aims to deduce the makeup of nucleotide sequences from the ionic current signals generated when passing DNA/RNA fragments through nanopores charged with a voltage difference. To determine the nucleotides from the measured signals, a translation process known as basecalling is required. However, compared to NGS basecallers, the calling accuracy of MinION still needs to be improved. In this work, a simple but powerful neural network architecture called MSRCall is proposed. MSRCall comprises a multi-scale structure, recurrent layers, a fusion block, and a CTC decoder. To better identify both short-range and long-range dependencies, the recurrent layer is redesigned to capture various time-scale features with a multi-scale structure. The results show that MSRCall outperforms other basecallers in terms of both read and consensus accuracies.

scholarly journals An Improved VGG19 Transfer Learning Strip Steel Surface Defect Recognition Deep Neural Network Based on Few Samples and Imbalanced Datasets

2021 ◽  
Vol 11 (6) ◽  
pp. 2606
Author(s):  
Xiang Wan ◽  
Xiangyu Zhang ◽  
Lilan Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Transfer Learning ◽  
Defect Detection ◽  
Data Augmentation ◽  
Projection Algorithm ◽  
Rapid Screening ◽  
Imbalanced Datasets ◽  
Strip Steel ◽  
Detection Techniques

The surface defects’ region of strip steel is small, and has various defect types and, complex gray structures. There tend to be a large number of false defects and edge light interference, which lead traditional machine vision algorithms to be unable to detect defects for various types of strip steel. Image detection techniques based on deep learning require a large number of images to train a network. However, for a dataset with few samples with category imbalanced defects, common deep learning neural network training tasks cannot be carried out. Based on rapid image preprocessing algorithms (improved gray projection algorithm, ROI image augmentation algorithm) and transfer learning theory, this paper proposes a set of processes for complete strip steel defect detection. These methods achieved surface rapid screening, defect feature extraction, sample dataset’s category balance, data augmentation, defect detection, and classification. Through verification of the mixed dataset, composed of the NEU surface dataset and dataset in this paper, the recognition accuracy of the improved VGG19 network in this paper reached 97.8%. The improved VGG19 network performs slightly better than the baseline VGG19 in six types of defects, but the improved VGG19 performs significantly better in the surface seams defects. The convergence speed and accuracy of the improved VGG19 network were taken into account, and the detection rate was greatly improved with few samples and imbalanced datasets. This paper also has practical value in terms of extending its method of strip steel defect detection to other products.

Damage detection in a novel deep-learning framework: a robust method for feature extraction

2019 ◽  
Vol 19 (2) ◽  
pp. 424-442 ◽  
Author(s):  
Tian Guo ◽  
Lianping Wu ◽  
Cunjun Wang ◽  
Zili Xu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Architecture ◽  
Mode Shapes ◽  
Damage Scenarios ◽  
Learning Modules ◽  
Learning Framework ◽  
Multi Scale ◽  
Extensive Evaluation ◽  
The Neural Network

Extracting damage features precisely while overcoming the adverse interferences of measurement noise and incomplete data is a problem demanding prompt solution in structural health monitoring (SHM). In this article, we present a deep-learning-based method that can extract the damage features from mode shapes without utilizing any hand-engineered feature or prior knowledge. To meet various requirements of the damage scenarios, we use convolutional neural network (CNN) algorithm and design a new network architecture: a multi-scale module, which helps in extracting features at various scales that can reduce the interference of contaminated data; stacked residual learning modules, which help in accelerating the network convergence; and a global average pooling layer, which helps in reducing the consumption of computing resources and obtaining a regression performance. An extensive evaluation of the proposed method is conducted by using datasets based on numerical simulations, along with two datasets based on laboratory measurements. The transferring parameter methodology is introduced to reduce retraining requirement without any decreases in precision. Furthermore, we plot the feature vectors of each layer to discuss the damage features learned at these layers and additionally provide the basis for explaining the working principle of the neural network. The results show that our proposed method has accuracy improvements of at least 10% over other network architectures.

Sign in / Sign up

Export Citation Format

Share Document