Enhanced YOLOv5 for micro-defect detection on KDP crystal surfaces: a fusion of EfficientNetV2 and normalized Wasserstein distance
Authors:
- 3 March 2025
- journal article
- research article
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 22 (2) , 1-12
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (52275420)
- National Key R&D Program of China (2022YFB3403304)
- Natural Science Foundation of Hunan Province (2022JJ30136)
This publication has 19 references indexed in Scilit:
- A dual-structure attention-based multi-level feature fusion network for automatic surface defect detectionThe Visual Computer, 2023
- YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors2023
- An Improved YOLOv5 Method for Small Object Detection in UAV Capture ScenesIEEE Access, 2023
- FE-YOLOv5: Feature enhancement network based on YOLOv5 for small object detectionJournal of Visual Communication and Image Representation, 2023
- OFF-eNET: An Optimally Fused Fully End-to-End Network for Automatic Dense Volumetric 3D Intracranial Blood Vessels SegmentationIEEE Transactions on Image Processing, 2020
- You Only Look Once: Unified, Real-Time Object Detection2016
- Study on mechanics and key technologies of laser nondestructive mirror-separation for KDP crystalInternational Journal of Machine Tools and Manufacture, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- EFFECT OF CRYSTALLOGRAPHIC ORIENTATION ON CUTTING FORCES AND SURFACE FINISH IN DUCTILE CUTTING OF KDP CRYSTALSMachining Science and Technology, 2011
- Investigation of anisotropic mechanisms in ultra-precision diamond machining of KDP crystalJournal of Materials Processing Technology, 2009