A Robotic Passive Vision System for Texture Analysis in Weld Beads

Soares, Luciane B.; Weis, Átila A.; Rodrigues, Ricardo; Botelho, Sílvia Silva da Costa

doi:10.1109/indin41052.2019.8972289

Cited by 8 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the weld seam can be identified by some feature recognition algorithms such as edge detection and contour extraction. For examples, Soares et al presented a computer vision system based on a passive monocular camera for analysis of weld bead textures (Soares et al, 2019). Images of weld beads are captured and Principal Component Analysis and Support Vector Machine method is applied to recognize the patterns of image groups.…”

Section: Related Workmentioning

confidence: 99%

Weld seam track identification for industrial robot based on illumination correction and center point extraction

LIANG

et al. 2022

JAMDSM

View full text Add to dashboard Cite

Weld shape and track precise identification is one of the key problems for automatic welding technology. In this paper, a weld track identification method based on illumination correction and center point extraction is proposed to extract welds with different shapes and non-uniform illumination. Firstly, an image pre-processing algorithm based on illumination correction is designed to eliminate the lighting influence. Secondly, an image extraction algorithm based on iterative threshold segmentation and morphological processing is proposed to obtain a continuous weld binary image. Thirdly, sub-pixel center point extraction algorithm and least-square based polynomial fitting is used to obtain the center fitting curve of welding seam. Experimental results show that the proposed method can realize accurate recognition of welding seam track under different illumination conditions effectively. The recognition error for welding seams with different typical shapes is within 4 pixels, and the average fitting error is less than 1.8 pixels. The welding seam identification and fitting method shows great application potential in the field of automatic assembling and robotic welding.

show abstract

Section: Related Workmentioning

confidence: 99%

Weld seam track identification for industrial robot based on illumination correction and center point extraction

LIANG

et al. 2022

JAMDSM

View full text Add to dashboard Cite

show abstract

A robotic passive vision system for texture analysis in weld beads

Soares

Costa

Botelho

et al. 2022

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

LoHi-WELD: A Novel Industrial Dataset for Weld Defect Detection and Classification, a Deep Learning Study, and Future Perspectives

Biasuz Block,

Dutra da Silva,

Eugnio Lazzaretti

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The automated inspection of weld beads is of great importance for many industrial processes. Failures may cause a loss of mechanical resistance of the weld bead and compromise the manufactured part. Several methods have been proposed in the literature to address this problem, and recently, methods based on deep learning have gained prominence in terms of performance and applicability. However, such methods require vast and reliable datasets for different real defects, which have yet to be available in recent literature. Hence, this paper presents LoHi-WELD, an original and public database to address the problem of weld defect detection and classification of four common types of defects -pores, deposits, discontinuities, and stains -with 3,022 real weld bead images manually annotated for visual inspection, composed by low and high-resolution images, acquired from a Metal Active Gas robotic welding industrial process. We also explore variations of a baseline deep architecture for the proposed dataset based on a YOLOv7 network and discuss several case analyses. We show that a lightweight architecture, ideal for industrial edge devices, can achieve up to 0.69 of mean average precision (mAP) considering a fine-grained defect classification and 0.77 mAP for a coarse classification. Open challenges are also presented, promoting future research and enabling robust solutions for industrial scenarios. The proposed dataset, architecture, and trained models are publicly available on GitHub a .

show abstract

A Robotic Passive Vision System for Texture Analysis in Weld Beads

Cited by 8 publications

References 6 publications

Weld seam track identification for industrial robot based on illumination correction and center point extraction

Weld seam track identification for industrial robot based on illumination correction and center point extraction

A robotic passive vision system for texture analysis in weld beads

LoHi-WELD: A Novel Industrial Dataset for Weld Defect Detection and Classification, a Deep Learning Study, and Future Perspectives

Contact Info

Product

Resources

About