A Multiscale Convolutional Registration Network for Defect Inspection on Periodic Lace Surfaces

Xu, Ding; Lu, Bingyu; Huang, Biqing

doi:10.1109/tim.2022.3150581

Cited by 2 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [14], a large lace dataset was proposed for the first time, which focused on the differences between the high-level semantic features extracted by the neural network, and a de-deformation defect detection network was proposed for lace surface defect detection. In order to fit the actual production scenario more, Xu et al [15] proposed a method for detecting and locating periodic lace surface defects, which only required defect-free image samples, reconstructed contrast tweens by extracting image tweens and their corresponding flaws to increase the morphological similarity of input image pairs, and then detected defects on the residual plot between the output and the image to be measured. However, these methods are only good at detecting lace hole and broken yarn, not friendly to other lace defects.…”

Section: Existing Defect Detection Methodsmentioning

confidence: 99%

Light-Trans YOLO: A Lightweight Network Based on Transformer for Defect Detection of Industrial Lace Surface

Wang,

Jing,

Sheng

2023

Preprint

View full text Add to dashboard Cite

Lace surface Defect detection has always been a crucial step in the industrial production of lace products. However, due to the complex texture and deforma-bility of lace, as well as the difficulty of distinguishing minor defects from normal images. Therefore, the detection of defects on lace surfaces is a challenging but rarely studied task. In this paper, we propose a new lightweight detection framework , Light-Trans YOLO, to detect lace surface defects. First, our backbone network uses the lightweight network C3 GhostNet. In addition, to obtain more complete global information, we add the lightweight Mobile Transformer Block (MTB) to the backbone network. Then we use the proposed standard deep-wise separable convolution (SDSConv) and SDSBottleneck to design a new neck and add Coordinate Attention (CA) at the end, which overcomes the problem of information loss of deep separable convolution and extracts more effective information. In the training, we propose the loss function ϵSIoU, which can improve the separability of defective and normal samples. We conduct experiments on the industrial lace surface defect dataset collected in lace production sites, and the experiments prove that the mAP of our model is 96.6%, which is 7.7% higher than YOLOV5s, and the FPS and F1-score of the model reaches 50.3 and 0.93, which indicates that our model has a great trade-off between detection accuracy and speed.

show abstract

Section: Existing Defect Detection Methodsmentioning

confidence: 99%