GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep Learning
Weld seam identification with industrial robots is a difficult task since it requires manual edge recognition and traditional image processing approaches, which take time. Furthermore, noises such as arc light, weld fumes, and different backgrounds have a significant impact on traditional weld seam...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/14/6860 |
_version_ | 1797441143698358272 |
---|---|
author | Abhilasha Singh Venkatesan Kalaichelvi Ashlyn DSouza Ram Karthikeyan |
author_facet | Abhilasha Singh Venkatesan Kalaichelvi Ashlyn DSouza Ram Karthikeyan |
author_sort | Abhilasha Singh |
collection | DOAJ |
description | Weld seam identification with industrial robots is a difficult task since it requires manual edge recognition and traditional image processing approaches, which take time. Furthermore, noises such as arc light, weld fumes, and different backgrounds have a significant impact on traditional weld seam identification. To solve these issues, deep learning-based object detection is used to distinguish distinct weld seam shapes in the presence of weld fumes, simulating real-world industrial welding settings. Genetic algorithm-based state-of-the-art object detection models such as Scaled YOLOv4 (You Only Look Once), YOLO DarkNet, and YOLOv5 are used in this work. To support actual welding, the aforementioned architecture is trained with 2286 real weld pieces made of mild steel and aluminum plates. To improve weld detection, the welding fumes are denoised using the generative adversarial network (GAN) and compared with dark channel prior (DCP) approach. Then, to discover the distinct weld seams, a contour detection method was applied, and an artificial neural network (ANN) was used to convert the pixel values into robot coordinates. Finally, distinct weld shape coordinates are provided to the TAL BRABO manipulator for tracing the shapes recognized using an eye-to-hand robotic camera setup. Peak signal-to-noise ratio, the structural similarity index, mean square error, and the naturalness image quality evaluator score are the dehazing metrics utilized for evaluation. For each test scenario, detection parameters such as precision, recall, mean average precision (mAP), loss, and inference speed values are compared. Weld shapes are recognized with 95% accuracy using YOLOv5 in both normal and post-fume removal settings. It was observed that the robot is able to trace the weld seam more precisely. |
first_indexed | 2024-03-09T12:18:44Z |
format | Article |
id | doaj.art-49ec0200aba64b77aa452bfa8323cbce |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T12:18:44Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-49ec0200aba64b77aa452bfa8323cbce2023-11-30T22:43:08ZengMDPI AGApplied Sciences2076-34172022-07-011214686010.3390/app12146860GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep LearningAbhilasha Singh0Venkatesan Kalaichelvi1Ashlyn DSouza2Ram Karthikeyan3Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science Pilani, Dubai Campus, Dubai P.O. Box 345 055, United Arab EmiratesDepartment of Electrical and Electronics Engineering, Birla Institute of Technology and Science Pilani, Dubai Campus, Dubai P.O. Box 345 055, United Arab EmiratesDepartment of Computer Science Engineering, Birla Institute of Technology and Science Pilani, Dubai Campus, Dubai P.O. Box 345 055, United Arab EmiratesDepartment of Mechanical Engineering, Birla Institute of Technology and Science Pilani, Dubai Campus, Dubai P.O. Box 345 055, United Arab EmiratesWeld seam identification with industrial robots is a difficult task since it requires manual edge recognition and traditional image processing approaches, which take time. Furthermore, noises such as arc light, weld fumes, and different backgrounds have a significant impact on traditional weld seam identification. To solve these issues, deep learning-based object detection is used to distinguish distinct weld seam shapes in the presence of weld fumes, simulating real-world industrial welding settings. Genetic algorithm-based state-of-the-art object detection models such as Scaled YOLOv4 (You Only Look Once), YOLO DarkNet, and YOLOv5 are used in this work. To support actual welding, the aforementioned architecture is trained with 2286 real weld pieces made of mild steel and aluminum plates. To improve weld detection, the welding fumes are denoised using the generative adversarial network (GAN) and compared with dark channel prior (DCP) approach. Then, to discover the distinct weld seams, a contour detection method was applied, and an artificial neural network (ANN) was used to convert the pixel values into robot coordinates. Finally, distinct weld shape coordinates are provided to the TAL BRABO manipulator for tracing the shapes recognized using an eye-to-hand robotic camera setup. Peak signal-to-noise ratio, the structural similarity index, mean square error, and the naturalness image quality evaluator score are the dehazing metrics utilized for evaluation. For each test scenario, detection parameters such as precision, recall, mean average precision (mAP), loss, and inference speed values are compared. Weld shapes are recognized with 95% accuracy using YOLOv5 in both normal and post-fume removal settings. It was observed that the robot is able to trace the weld seam more precisely.https://www.mdpi.com/2076-3417/12/14/6860robotic weldingGANScaled YOLOv4TAL BRABO robotic manipulatorPSNRSSIM |
spellingShingle | Abhilasha Singh Venkatesan Kalaichelvi Ashlyn DSouza Ram Karthikeyan GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep Learning Applied Sciences robotic welding GAN Scaled YOLOv4 TAL BRABO robotic manipulator PSNR SSIM |
title | GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep Learning |
title_full | GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep Learning |
title_fullStr | GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep Learning |
title_full_unstemmed | GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep Learning |
title_short | GAN-Based Image Dehazing for Intelligent Weld Shape Classification and Tracing Using Deep Learning |
title_sort | gan based image dehazing for intelligent weld shape classification and tracing using deep learning |
topic | robotic welding GAN Scaled YOLOv4 TAL BRABO robotic manipulator PSNR SSIM |
url | https://www.mdpi.com/2076-3417/12/14/6860 |
work_keys_str_mv | AT abhilashasingh ganbasedimagedehazingforintelligentweldshapeclassificationandtracingusingdeeplearning AT venkatesankalaichelvi ganbasedimagedehazingforintelligentweldshapeclassificationandtracingusingdeeplearning AT ashlyndsouza ganbasedimagedehazingforintelligentweldshapeclassificationandtracingusingdeeplearning AT ramkarthikeyan ganbasedimagedehazingforintelligentweldshapeclassificationandtracingusingdeeplearning |