Study on Feature Extraction of Cable Surface Defect Image Based on Morphology and Edge Detection Algorithm

Hu, Jing; He, Hongyu; Liao, Guomin; Hu, Guichuan

doi:10.1088/1742-6596/2035/1/012021

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lin et al [6] proposed an improved mean-c local threshold method and a oneshot machine-vision method based on a texture orientation histogram to detect defects on the surface of metal parts. Hu et al [7] studied feature extraction from cable surface defect images based on a morphology and edge detection algorithm. However, the above defect detection methods mostly extract features by manual design, and the detection accuracy and speed are relatively low, which unable to meet the demands of actual complex tasks.…”

Section: Introductionmentioning

confidence: 99%

ESDDNet: efficient small defect detection network of workpiece surface

Chen¹,

Xu²,

Liu³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Defect detection of workpiece surface is a basic and essential task in the production of workpiece products. Although significant progress has been made in workpiece surface defect detection, traditional methods are still difficult to detect small defects efficiently. To deal with this problem, an efficient small defect detection network (ESDDNet) with novel parallel convolution module, serial convolution module and feature fusion module is proposed. Firstly, lightweight backbone network is used to extract preliminary defect features. Secondly, the parallel convolution module and serial convolution module are used to obtain abundant defect features. Then, the feature fusion module is used to fuse shallow features with deep features to enhance the features of small defects. Finally, the obtained features are put into the corresponding detection head to get the final prediction results. The experimental results on local cable dataset and public PCB dataset show that our method achieves remarkable performance in detecting small defects and achieves favorable trade-off between accuracy, speed and model size, which meets the requirements of industrial application.

show abstract

Section: Introductionmentioning

confidence: 99%

ESDDNet: efficient small defect detection network of workpiece surface

Chen¹,

Xu²,

Liu³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Squeeze-and-excitation attention and bi-directional feature pyramid network for filter screens surface detection

Xu,

Zhu,

Shi

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Based on the enhanced YOLOv5, a deep learning defect detection technique is presented to deal with the problem of inadequate effectiveness in manually detecting problems on the surface of filter screens. In the last layer of the backbone network, the method combines the squeeze-and-excitation attention mechanism module, the method assigns weights to image locations based on the channel domain perspective to obtain more feature information. It also compares the results with a simple, parameter-free attention model (SimAM), which is an attention mechanism without the channel domain, and the results are higher than SimAM 0.7%. In addition, the neck network replaces the basic PANet structure with the bi-directional feature pyramid network module, which introduces multi-scale feature fusion. The experimental results show that the improved YOLOv5 algorithm has an average defect detection accuracy of 97.7% on the dataset, which is 11.3%, 12.8%, 2%, 7.8%, 5.1%, and 1.3% higher than YOLOv3, faster R-CNN, YOLOv5, SSD, YOLOv7, and YOLOv8, respectively. It can quickly and accurately identify various defects on the surface of the filter, which has an outstanding contribution to the filter manufacturing industry.

show abstract

Study on Feature Extraction of Cable Surface Defect Image Based on Morphology and Edge Detection Algorithm

Cited by 2 publications

References 0 publications

ESDDNet: efficient small defect detection network of workpiece surface

ESDDNet: efficient small defect detection network of workpiece surface

Squeeze-and-excitation attention and bi-directional feature pyramid network for filter screens surface detection

Contact Info

Product

Resources

About