WGWenhui Guan
Wenhui Guan
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wenhui Guan has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chenglin Cai
Xiangtan University
2 shared publications - Zexian Li
School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China
2 shared publications - Feng Yin
College of Automation and Electronic Information, Xiangtan University, Xiangtan, China
1 shared publication - Keyu Li
Xiangtan University
1 shared publication - Lingfeng Cheng
School of Mathematical and Computational Sciences, Xiangtan University, Xiangtan 411105, China
1 shared publication - Qin Liang
Xiangtan University
1 shared publication
Latest Publications
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
Lightweight Segmentation Neural Networks for Measuring Vickers Hardness
The automatic measurement algorithm for Vickers hardness indentation has been widely applied. Among these, the neural network-based method has received attention for its excellent segmentation performance. However, high storage space and computation requirements hinder its promotion on edge computing devices. To address this issue, this study proposes two lightweight Vickers indentation segmentation networks: VSNLite4M and VSNLite1M. Compared with previous methods, the proposed networks achieve a reduction of$35.2\times $ in terms of computational cost with up to$38\times $ fewer parameters, while maintaining the same level of segmentation accuracy.- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
Lightweight Segmentation Neural Networks for Measuring Vickers Hardness
The automatic measurement algorithm for Vickers hardness indentation has been widely applied. Among these, the neural network-based method has received attention for its excellent segmentation performance. However, high storage space and computation requirements hinder its promotion on edge computing devices. To address this issue, this study proposes two lightweight Vickers indentation segmentation networks: VSNLite4M and VSNLite1M. Compared with previous methods, the proposed networks achieve a reduction of$35.2\times $ in terms of computational cost with up to$38\times $ fewer parameters, while maintaining the same level of segmentation accuracy.