An efficient lightweight convolutional neural network for industrial surface defect detection

Zhang, Dehua; Hao, Xinyuan; Wang, Dechen; Qin, Chunbin; Zhao, Bo; Liang, Li‐Jung; Liu, Wei

doi:10.1007/s10462-023-10438-y

Cited by 26 publications

(12 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The robustness of using multi-scale features is shown to adapt to the diversity of defect shapes. In further studies [ 62 , 63 , 64 , 65 ], researchers have obtained the full-scale features to detect defects of multiple scales using a multi-scale feature fusion network.…”

Section: Related Workmentioning

confidence: 99%

DAssd-Net: A Lightweight Steel Surface Defect Detection Model Based on Multi-Branch Dilated Convolution Aggregation and Multi-Domain Perception Detection Head

et al. 2023

Sensors

View full text Add to dashboard Cite

During steel production, various defects often appear on the surface of the steel, such as cracks, pores, scars, and inclusions. These defects may seriously decrease steel quality or performance, so how to timely and accurately detect defects has great technical significance. This paper proposes a lightweight model based on multi-branch dilated convolution aggregation and multi-domain perception detection head, DAssd-Net, for steel surface defect detection. First, a multi-branch Dilated Convolution Aggregation Module (DCAM) is proposed as a feature learning structure for the feature augmentation networks. Second, to better capture spatial (location) information and to suppress channel redundancy, we propose a Dilated Convolution and Channel Attention Fusion Module (DCM) and Dilated Convolution and Spatial Attention Fusion Module (DSM) as feature enhancement modules for the regression and classification tasks in the detection head. Third, through experiments and heat map visualization analysis, we have used DAssd-Net to improve the receptive field of the model while paying attention to the target spatial location and redundant channel feature suppression. DAssd-Net is shown to achieve 81.97% mAP accuracy on the NEU-DET dataset, while the model size is only 18.7 MB. Compared with the latest YOLOv8 model, the mAP increased by 4.69%, and the model size was reduced by 23.9 MB, which has the advantage of being lightweight.

show abstract

Section: Related Workmentioning

confidence: 99%

DAssd-Net: A Lightweight Steel Surface Defect Detection Model Based on Multi-Branch Dilated Convolution Aggregation and Multi-Domain Perception Detection Head

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Additionally, they design a novel bidirectional weighted feature pyramid network (BWFPN) to improve the detection accuracy of the model. 16 Niu et al utilize the K-means+ + method to enhance the matching of prior anchor boxes. Furthermore, the Focal-EIOU loss function is employed as a replacement for GIOU to address the degradation issue, thereby improving the localization capability of PCB defects.…”

Section: Introductionmentioning

confidence: 99%

“…integrate the inverse residual (IR) structure with the coordinate attention (CA) mechanism to construct a backbone network called CA Module for feature extraction. Additionally, they design a novel bidirectional weighted feature pyramid network (BWFPN) to improve the detection accuracy of the model 16 . Niu et al.…”

Section: Introductionmentioning

confidence: 99%

WDC-YOLO: an improved YOLO model for small objects oriented printed circuit board defect detection

Song,

Wang,

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

The detection of surface defects on a printed circuit board (PCB) plays a crucial role in ensuring the quality of PCB products. To address the diversity of defect poses and the challenges associated with detecting small objects on PCB, this paper proposes an improved YOLOv7 model for small objects-oriented PCB defect detection. First, this paper improves the regression loss function of YOLOv7 by incorporating wise-IoU (WIoU) and replacing IoU with an outlier degree to develop a gradient-boosting allocation strategy, thereby increasing the network's accuracy. Second, this paper proposes a coordinate attention dynamic mechanism that performs convolution operations with deformable convolutional networks v2 (DCNv2) using coordinate attention. This mechanism effectively suppresses redundant information. Finally, this paper proposes a dynamic head diverse (DyHead-d) module that prioritizes spatial awareness over scale awareness, building on DyHead. This module improves the network's ability to localize small targets. Experimental results show that the WDC-YOLO achieves a mean average precision of 98.4% on public datasets, demonstrating a 3.1% improvement compared to the original network. The significantly enhanced detection accuracy meets the real-time requirements of PCB defect diagnosis, which is of great importance for quality control and cost reduction in PCB industrial production.

show abstract

“…Industrial defect detection aims to automatically identify and locate defects or anomalies in products of different materials, e.g., glass or steel, etc (Zhang et al 2023a). These defects or anomalies may include surface defects, cuts, cracks, deformations, size deviations, and other issues that could impact the quality and safety of the materials.…”

Section: Introductionmentioning

confidence: 99%

Automated Defect Report Generation for Enhanced Industrial Quality Control

Xie,

Zhou,

et al. 2024

AAAI

View full text Add to dashboard Cite

Defect detection is a pivotal aspect ensuring product quality and production efficiency in industrial manufacturing. Existing studies on defect detection predominantly focus on locating defects through bounding boxes and classifying defect types. However, their methods can only provide limited information and fail to meet the requirements for further processing after detecting defects. To this end, we propose a novel task called defect detection report generation, which aims to provide more comprehensive and informative insights into detected defects in the form of text reports. For this task, we propose some new datasets, which contain 16 different materials and each defect contains a detailed report of human constructs. In addition, we propose a knowledge-aware report generation model as a baseline for future research, which aims to incorporate additional knowledge to generate detailed analysis and subsequent processing related to defect in images. By constructing defect report datasets and proposing corresponding baselines, we chart new directions for future research and practical applications of this task.

show abstract

An efficient lightweight convolutional neural network for industrial surface defect detection

Cited by 26 publications

References 61 publications

DAssd-Net: A Lightweight Steel Surface Defect Detection Model Based on Multi-Branch Dilated Convolution Aggregation and Multi-Domain Perception Detection Head

DAssd-Net: A Lightweight Steel Surface Defect Detection Model Based on Multi-Branch Dilated Convolution Aggregation and Multi-Domain Perception Detection Head

WDC-YOLO: an improved YOLO model for small objects oriented printed circuit board defect detection

Automated Defect Report Generation for Enhanced Industrial Quality Control

Contact Info

Product

Resources

About