Defect Detection for Metal Base of TO-Can Packaged Laser Diode Based on Improved YOLO Algorithm

Liu, Jiayi; Zhu, Xuding; Zhou, Xingyu; Qian, Shanhua; Yu, Jinghu

doi:10.3390/electronics11101561

Cited by 25 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Before the backbone network conducts feature extraction, the input data undergoes enhancement through Mosaic [26] and Mixup [27]. To enhance network robustness, nine images are stitched into a single image through random scaling, cropping, and scheduling.…”

Section: Stae-yolo Network Modelmentioning

confidence: 99%

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

Ji,

Zhang,

Huang

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

The distribution of transmission lines is complex, influenced by terrain and topography, making their maintenance and management challenging. With the advancement of global mechanization, various types of construction machinery and large‐scale mechanical equipment are continually increasing. Accidental contact of construction machinery near transmission lines poses a serious threat to the stability of the power system. Traditional drones and inspection robots face difficulties in achieving real‐time monitoring of construction machinery and equipment around transmission lines, quickly identifying potential risks. Conventional image processing techniques and convolutional neural networks struggle with effective handling of small targets and densely packed detection tasks involving multiple targets. To address these challenges, this paper proposes an intelligent detection algorithm Swin Transformer attention efficient algorithm‐you only look once (YOLO) (STAE‐YOLO). It is based on the Swin Transformer global self‐attention mechanism, cross‐channel fusion attention mechanism, enhanced small object detection framework, and a focused and efficient regression loss function. The experimental results show that the STAE‐YOLO algorithm model improved by 6.3% in mean average precision, 3.7% in precision, and 3.1% in recall compared to the baseline model. Meanwhile, deploying the window multi‐head self‐attention global self‐attention mechanism in the model can strengthen the global multi‐scale semantic information in detection.

show abstract

Section: Stae-yolo Network Modelmentioning

confidence: 99%

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

Ji,

Zhang,

Huang

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…It can be inferred from the above research that the biggest problem of the current product defect detection method is the contradiction between detection accuracy and detection speed. To achieve real-time detection while improving detection accuracy, Jiayi Liu [27] proposed to improve the convolutional layer of the backbone network and reduce the sensitivity to the initial clustering center, which can achieve fast detection while ensuring the correct rate of detection classification.…”

Section: Related Workmentioning

confidence: 99%

The RFID Electronic Tag Defect Detection System Based On YOLOv5 For Industrial Scenarios

Zhou¹,

Ding²,

Du³

et al. 2022

Proceedings of International Exchange and Innovation Conference on Engineering &Amp; Sciences (IEICES)

View full text Add to dashboard Cite

Recent technological progress has promoted a large number of development trends in the Radio Frequency Identification (RFID) system. RFID tag detection/identification is one of the most critical problems in successfully deploying the RFID system in various applications. However, many significant issues related to detecting RFID tag defects have not been addressed. The main problems of RFID electronic tag defect detection methods in industrial scenarios are low efficiency, low accuracy, and high labor costs. This paper analyses the characteristics of RFID tag defects based on defect samples, and a detection and prediction method related to YOLOv5 is proposed. In this experiment, a real-time RFID tag defect intelligent detection system embedded in the YOLOv5 model was developed and applied to industrial production. The results show that this system has higher accuracy in defect detection, faster detection time, and saves labor costs, which can meet industrial needs.

show abstract

“…Lee and Hwang [ 22 ] proposed a novel YOLO architecture with adaptive frame control to solve the real‐time processing of objects using network cameras, which provides efficient guidelines for appropriate hardware platform selection. To detect the appearance defects of transistor outline package laser diodes, Liu et al [ 23 ] improved the YOLO algorithm in three aspects: adding a convolutional block attention mechanism module, proposing a random‐paste‐mosaic small object data augmentation module, and applying the K‐means++ clustering algorithm. Xu et al [ 24 ] developed a lightweight DL detector for an on‐board ship detection method based on YOLOv5 in large‐scene sentinel‐1 synthetic aperture radar images to reduce the detection model volume and floating‐point operations.…”

Section: Introductionmentioning

confidence: 99%

YOLOv5s‐GC‐Based Surface Defect Detection Method of Strip Steel

Li,

Yang,

Zhou

2024

steel research int.

View full text Add to dashboard Cite

Detecting surface defects in strip steel is significantly important for improving production efficiency and product quality. Herein, a novel surface defect detection of strip steel method based on You Only Look Once (YOLO)v5s‐GC is proposed. First, a ResNet‐Mini is developed to preclassify the original dataset to reduce the number of calculations. Subsequently, image preprocessing is conducted to enhance the defect features, which consists of two steps: the first is combining the ResNet‐Mini network weights with Grad‐CAM to crop defective areas and remove background interference and the second is applying the OTSU and normal distribution enhancement algorithm to extract the feature grayscale. Furthermore, a size enhancement strategy is adopted to obtain larger data sizes that could simulate an actual application scenario with a large‐area saccade of strip steel. Finally, the cross‐stage partial module of YOLOv5s is replaced with GhostBottleneck, and the convolutional block attention module is added to the detection neck. The average accuracy of YOLOv5s‐GC for detecting six types of strip steel is 82.4%, marking an increase of 7.0% over YOLOv5s. In addition, the calculation amount of YOLOv5s‐GC is reduced by 48%, and the inference speed is increased by 24%.

show abstract

Defect Detection for Metal Base of TO-Can Packaged Laser Diode Based on Improved YOLO Algorithm

Cited by 25 publications

References 33 publications

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

The RFID Electronic Tag Defect Detection System Based On YOLOv5 For Industrial Scenarios

YOLOv5s‐GC‐Based Surface Defect Detection Method of Strip Steel

Contact Info

Product

Resources

About