scholarly journals Synthetic Data Generation for Steel Defect Detection and Classification Using Deep Learning

Symmetry ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 1176
Author(s):  
Aleksei Boikov ◽  
Vladimir Payor ◽  
Roman Savelev ◽  
Alexandr Kolesnikov
Keyword(s):  
Neural Networks ◽  
Defect Detection ◽  
Production Control ◽  
Surface Defects ◽  
Synthetic Data ◽  
Real Data ◽  
Data Generation ◽  
Synthetic Data Generation ◽  
Steel Slab ◽  
Defect Recognition

The paper presents a methodology for training neural networks for vision tasks on synthesized data on the example of steel defect recognition in automated production control systems. The article describes the process of dataset procedural generation of steel slab defects with a symmetrical distribution. The results of training two neural networks Unet and Xception on a generated data grid and testing them on real data are presented. The performance of these neural networks was assessed using real data from the Severstal: Steel Defect Detection set. In both cases, the neural networks showed good results in the classification and segmentation of surface defects of steel workpieces in the image. Dice score on synthetic data reaches 0.62, and accuracy—0.81.

Towards synthetic data generation for machine learning models in weather and climate

2020 ◽  
Author(s):  
David Meyer
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Climate Models ◽  
Synthetic Data ◽  
Real Data ◽  
Data Generation ◽  
Learning Models ◽  
Synthetic Data Generation ◽  
Weather And Climate ◽  
Machine Learning Models

<p>The use of real data for training machine learning (ML) models are often a cause of major limitations. For example, real data may be (a) representative of a subset of situations and domains, (b) expensive to produce, (c) limited to specific individuals due to licensing restrictions. Although the use of synthetic data are becoming increasingly popular in computer vision, ML models used in weather and climate models still rely on the use of large real data datasets. Here we present some recent work towards the generation of synthetic data for weather and climate applications and outline some of the major challenges and limitations encountered.</p>

scholarly journals SynSys: A Synthetic Data Generation System for Healthcare Applications

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1181 ◽  
Author(s):  
Jessamyn Dahmen ◽  
Diane Cook
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Synthetic Data ◽  
Real Data ◽  
Series Data ◽  
Data Generation ◽  
Healthcare Applications ◽  
Ground Truth Data ◽  
Generation Technique ◽  
Synthetic Data Generation

Creation of realistic synthetic behavior-based sensor data is an important aspect of testing machine learning techniques for healthcare applications. Many of the existing approaches for generating synthetic data are often limited in terms of complexity and realism. We introduce SynSys, a machine learning-based synthetic data generation method, to improve upon these limitations. We use this method to generate synthetic time series data that is composed of nested sequences using hidden Markov models and regression models which are initially trained on real datasets. We test our synthetic data generation technique on a real annotated smart home dataset. We use time series distance measures as a baseline to determine how realistic the generated data is compared to real data and demonstrate that SynSys produces more realistic data in terms of distance compared to random data generation, data from another home, and data from another time period. Finally, we apply our synthetic data generation technique to the problem of generating data when only a small amount of ground truth data is available. Using semi-supervised learning we demonstrate that SynSys is able to improve activity recognition accuracy compared to using the small amount of real data alone.

Synthetic data generation of high-resolution hyperspectral data using DIRSIG

2007 ◽  
Author(s):  
Marek K. Jakubowski ◽  
David Pogorzala ◽  
Timothy J. Hattenberger ◽  
Scott D. Brown ◽  
John R. Schott
Keyword(s):  
High Resolution ◽  
Synthetic Data ◽  
Hyperspectral Data ◽  
Data Generation ◽  
Synthetic Data Generation

Synthetic Data Generation to Support Irregular Sampling in Sensor Networks

2004 ◽  
pp. 211-234 ◽  
Author(s):  
Lewis Girod ◽  
Ramesh Govindan ◽  
Deepak Ganesan ◽  
Deborah Estrin ◽  
Yan Yu
Keyword(s):  
Sensor Networks ◽  
Synthetic Data ◽  
Irregular Sampling ◽  
Data Generation ◽  
Synthetic Data Generation

scholarly journals Applicationof Computer Visionfor Polishing RobotinAutomotive Manufacturing Industries

2014 ◽  
Vol 2 (2) ◽  
Author(s):  
Adnan Rachmat Anom Besari ◽  
Ruzaidi Zamri ◽  
Md. Dan Md. Palil ◽  
Anton Satria Prabuwono
Keyword(s):  
Neural Networks ◽  
Surface Roughness ◽  
Artificial Neural Networks ◽  
Surface Defects ◽  
Vision System ◽  
Real Data ◽  
Surface Measurement ◽  
Vision Sensor ◽  
Skilled Workers ◽  
Artificial Neural

Polishing is a highly skilled manufacturing process with a lot of constraints and interaction with environment. In general, the purpose of polishing is to get the uniform surface roughness distributed evenly throughout part’s surface. In order to reduce the polishing time and cope with the shortage of skilled workers, robotic polishing technology has been investigated. This paper studies about vision system to measure surface defects that have been characterized to some level of surface roughness. The surface defects data have learned using artificial neural networks to give a decision in order to move the actuator of arm robot. Force and rotation time have chosen as output parameters of artificial neural networks. Results shows that although there is a considerable change in both parameter values acquired from vision data compared to real data, it is still possible to obtain surface defects characterization using vision sensor to a certain limit of accuracy. The overall results of this research would encourage further developments in this area to achieve robust computer vision based surface measurement systems for industrial robotic, especially in polishing process.Keywords: polishing robot, vision sensor, surface defects, and artificial neural networks

scholarly journals Instance Segmentation in CARLA: Methodology and Analysis for Pedestrian-oriented Synthetic Data Generation in Crowded Scenes

2021 ◽  
Author(s):  
Maria Lyssenko ◽  
Christoph Gladisch ◽  
Christian Heinzemann ◽  
Matthias Woehrle ◽  
Rudolph Triebel
Keyword(s):  
Synthetic Data ◽  
Data Generation ◽  
Synthetic Data Generation ◽  
Crowded Scenes ◽  
Instance Segmentation

Synthetic Data Generation Capabilties for Testing Data Mining Tools

MILCOM 2006 ◽  
2006 ◽  
Author(s):  
Daniel Jeske ◽  
Pengyue Lin ◽  
Carlos Rendon ◽  
Rui Xiao ◽  
Behrokh Samadi
Keyword(s):  
Data Mining ◽  
Synthetic Data ◽  
Data Generation ◽  
Synthetic Data Generation ◽  
Testing Data ◽  
Mining Tools
Sign in / Sign up

Export Citation Format

Share Document