Defect Detection of MEMS Based on Data Augmentation, WGAN-DIV-DC, and a YOLOv5 Model

Abstract

Surface defect detection of micro-electromechanical system (MEMS) acoustic thin film plays a crucial role in MEMS device inspection and quality control. The performances of deep learning object detection models are significantly affected by the number of samples in the training dataset. However, it is difficult to collect enough defect samples during production. In this paper, an improved YOLOv5 model was used to detect MEMS defects in real time. Mosaic and one more prediction head were added into the YOLOv5 baseline model to improve the feature extraction capability. Moreover, Wasserstein divergence for generative adversarial networks with deep convolutional structure (WGAN-DIV-DC) was proposed to expand the number of defect samples and to make the training samples more diverse, which improved the detection accuracy of the YOLOv5 model. The optimal detection model achieved 0.901 mAP, 0.856 F1 score, and a real-time speed of 75.1 FPS. As compared with the baseline model trained using a non-augmented dataset, the mAP and F1 score of the optimal detection model increased by 8.16% and 6.73%, respectively. This defect detection model would provide significant convenience during MEMS production.

High Quality Coal Foreign Object Image Generation Method Based on StyleGAN-DSAD

“…With scholars’ in-depth research on GAN, several works, such as WGAN [ 14 ], WGAN-GP [ 15 ], DCGAN [ 16 ], ProGAN [ 17 ], and BigGAN [ 18 ], have been introduced to gradually improve the training stability of GAN and the resolution of generated images, which laid the foundation for its application in machine vision tasks. Shi [ 19 ] added Wasserstein divergence to WGAN to improve the diversity of defect samples on the surface of micro-electromechanical systems (MEMS), and the experimental results showed that the mAP and F1 scores of defect detection were improved by 8.16% and 6.73%, respectively, after data augmentation. Deng [ 20 ] applied WGAN-GP to data augmentation for facial expression recognition, and improved the recognition accuracy of multi-angle facial expressions.…”