One-stage object detection networks for inspecting the surface defects of magnetic tiles

Wei, Jiaqi; Zhu, Peiyuan; Qian, Xiang; Zhu, Shidong

doi:10.1109/ist48021.2019.9010098

Cited by 7 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, due to their high hardness and brittleness, they are prone to defects during the manufacturing process, which can adversely affect the performance and lifespan of permanent magnet motors. These defects include external flaws such as fractures and burrs, as well as internal flaws like cracks and voids [4,5]. To reduce production costs and improve efficiency, nondestructive testing of internal and external defects in ferrite tiles is required before they are magnetized to become magnetic tile products.…”

Section: Introductionmentioning

confidence: 99%

A Through-Transmission Ultrasonic Method for the Detection of Ferrite Tile Defects

Huang,

Li,

Zhu

et al. 2023

Applied Sciences

Self Cite

View full text Add to dashboard Cite

A through-transmission ultrasonic method is proposed to address limitations in conventional ultrasonic reflection methods for non-destructive testing of ferrite tiles. The method utilizes a dual-probe configuration on both sides of the test piece to measure ultrasonic transmission signals, overcoming issues related to blind zones and orientation limitations in pulse-echo reflection methods. This method demonstrates excellent capabilities for full inspection of internal and external defects in ferrite tiles. Physical field finite element simulations were conducted to analyze detection capabilities and a transmissive testing system is developed based on the simulation results. Experimental validation was performed on artificially manufactured quantified defect samples in aluminum alloy, and the same testing system was applied to evaluate ferrite tile samples. The results confirmed the effectiveness of the system in distinguishing defective (NG) signals from normal defect-free (OK) signals, with a recall rate of at least 95% on samples of various sizes up to 0.1 mm. This research provides insights for quality control and defect detection technology in ferrite tiles.

show abstract

Section: Introductionmentioning

confidence: 99%

A Through-Transmission Ultrasonic Method for the Detection of Ferrite Tile Defects

Huang,

Li,

Zhu

et al. 2023

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…As one of the most fundamental and challenging problems in computer vision, object detection has been widely applied in various industrial fields, such as surveillance, 18 autonomous driving, 19 and the surface defect detection of magnetic tiles. 20 Existing object detectors usually can be divided into two categories: 21 one is the two-stage detector (e.g., Faster R-CNN 22 and Mask R-CNN 23 ), and the other is the one-stage detector (e.g., You Only Look Once (YOLO), [24][25][26] Single Shot MultiBox Detector (SSD), 27 and RetinaNet. 28 The two stages of two-stage detectors can be divided by the ROI (Region of Interest) pooling layer.…”

Section: Introductionmentioning

confidence: 99%

An Improved Fabric Defect Detection Method Based on SSD

Xie

Zhang

2021

AATCC Journal of Research

View full text Add to dashboard Cite

The fabric defect detection algorithm based on object detection has become a research hotspot. The method based on the Single Shot MultiBox Detector (SSD) model has a fast detection speed, but the detection accuracy is insufficient. To balance the detection speed and accuracy of the model and meet the actual needs of the industry, an improved fabric defect detection algorithm based on SSD is proposed in this study. The Fully Convolutional Squeeze-and-Excitation (FCSE) block is added into the traditional SSD to improve the detection accuracy of the model. The number of default boxes was adjusted to accommodate the detection of long strip defects on fabric surface. Experimental results on the TILDA and Xuelang dataset confirm that our detection method based on SSD efficiently detected various fabric defects.

show abstract

“…Zhang et al [21] verified the performance of three variants of YOLOv2 models and proposed a yarn-dyed fabric defect automatic localization and classification method. Wei et al [22] designed three models based on YOLOv3 to detect the surface defects on magnetic tiles. Jing et al [8] introduced the YOLOv3 model to fabric defect detection and added a lower feature layer to the feature pyramid.…”

Section: Introductionmentioning

confidence: 99%

A Robust Fabric Defect Detection Method Based on Improved RefineDet

Xie

2020

Sensors

View full text Add to dashboard Cite

This paper proposes a robust fabric defect detection method, based on the improved RefineDet. This is done using the strong object localization ability and good generalization of the object detection model. Firstly, the method uses RefineDet as the base model, inheriting the advantages of the two-stage and one-stage detectors and can efficiently and quickly detect defect objects. Secondly, we design an improved head structure based on the Full Convolutional Channel Attention (FCCA) block and the Bottom-up Path Augmentation Transfer Connection Block (BA-TCB), which can improve the defect localization accuracy of the method. Finally, the proposed method applies many general optimization methods, such as attention mechanism, DIoU-NMS, and cosine annealing scheduler, and verifies the effectiveness of these optimization methods in the fabric defect localization task. Experimental results show that the proposed method is suitable for the defect detection of fabric images with unpattern background, regular patterns, and irregular patterns.

show abstract

One-stage object detection networks for inspecting the surface defects of magnetic tiles

Cited by 7 publications

References 11 publications

A Through-Transmission Ultrasonic Method for the Detection of Ferrite Tile Defects

A Through-Transmission Ultrasonic Method for the Detection of Ferrite Tile Defects

An Improved Fabric Defect Detection Method Based on SSD

A Robust Fabric Defect Detection Method Based on Improved RefineDet

Contact Info

Product

Resources

About