Five deep learning recipes for the mask-making industry

Baranwal, Ajay Kumar; Meyer, Mike; Nguyen, Thang; Pillai, Suhas; Nakayamada, Noriaki; Wahlsten, Mikael; Fujimura, Aki; Niewczas, Mariusz; Pomerantsev, Michael

doi:10.1117/12.2538440

Cited by 3 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baranwal et al used VGG16 to propose a classification model for correctly placing surface mount components during PCB assembly. The classification accuracy was higher than trained artificial vision classification [46]. Shen et al proposed a PCB defect detection model after assembly.…”

Section: Electronic Component Detection In Pcb Assembly Scenementioning

confidence: 98%

“…For the electronic component detection problem in the PCB assembly scene, the current research mainly includes six aspects: small size object detection [37,38], PCB positioning [39,40], electronic component detection [41][42][43][44][45][46], model lightweight [47,48] and real-time detection [49,50]. Li et al proposed a detection method for small-sized PCB electronic components based on multiple detection heads.…”

Section: Electronic Component Detection In Pcb Assembly Scenementioning

confidence: 99%

See 1 more Smart Citation

Balanced-YOLOv3: Addressing the Imbalance Problem of Object Detection in PCB Assembly Scene

Chen

et al. 2022

Electronics

View full text Add to dashboard Cite

The object detection algorithm of the PCB (Printed Circuit Board) assembly scene based on CNN (Convolutional Neural Network) can significantly improve the production capacity of intelligent manufacturing of electronic products. However, the object class imbalance in the PCB assembly scene, the multi-scale feature imbalance, and the positive/negative sample imbalance in the CNN have become critical problems restricting object detection performance. Based on YOLOv3, this paper proposes a class-balanced Train/Val (Training set/Validation set) split method for object class imbalance, an additional feature fusion strategy for multi-scale feature imbalance, and an efficient anchor concept for positive/negative sample imbalance. These three contributions are Balanced-YOLOv3. After experimental verification, compared with other YOLOv3 series algorithms, the mAP@.5 (Mean Average Precision at Intersection over Union threshold 0.5) and mAP@.5:.95 (average mAP over different Intersection over Union thresholds, from 0.5 to 0.95, step 0.05) of Balanced-YOLOv3 have achieved the best results and ranked third in the metrics of parameter and inference time. Compared with other current anchor-based object detection algorithms, Balanced-YOLOv3 has excellent detection performance and low computational complexity, which effectively solves the problem of imbalanced object detection in PCB assembly scenarios.

show abstract

Section: Electronic Component Detection In Pcb Assembly Scenementioning

confidence: 98%