Yanqi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yanqi Wang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Zheng Xu
School of Mechanical Engineering, Dalian University of Technology, Dalian 116024, China
3 shared publications Jiaheng He
Key Laboratory for Micro/Nano Technology and System of Liaoning Province, Dalian University of Technology, Dalian, People’s Republic of China
2 shared publicationsXiaodong Wang
Key Laboratory for Micro/Nano Technology and System of Liaoning Province, Dalian University of Technology, Dalian, People’s Republic of China
2 shared publications- Xiaodong Wang
Dalian University of Technology
2 shared publications - Gang Han
School of Mechanical Engineering, Dalian University of Technology, Dalian 116024, China
1 shared publication - Hongyu Du
School of Mechanical Engineering, Dalian University of Technology, Dalian 116024, China
1 shared publication
Latest Publications
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
An Improved SRGAN-Based Deblurring Model for Multiple Blurriness in Microscopy
In microscopy, eliminating blurriness and obtaining a sharp and accurate edge of observed objects in multiple blurriness is a key issue. Herein, a deblurring model called De-SRGAN is proposed, in which multiple discriminators are set. The multi-discriminators architecture can provide stable training, which helps achieve effective deblurring results in multiple blurriness. Moreover, considering the property of the edge in the frequency domain, a perceptual loss term in the frequency domain is constructed as additional factor. Results show that De-SRGAN can generate deblurred images with low MSE/ MAE, high PSNR/SSIM, high perceptual quality, and high accuracy. This study contributes to improving the accuracy of size measurement due to the deblurred images with sharp and accurate edges.
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
An Improved SRGAN-Based Deblurring Model for Multiple Blurriness in Microscopy
In microscopy, eliminating blurriness and obtaining a sharp and accurate edge of observed objects in multiple blurriness is a key issue. Herein, a deblurring model called De-SRGAN is proposed, in which multiple discriminators are set. The multi-discriminators architecture can provide stable training, which helps achieve effective deblurring results in multiple blurriness. Moreover, considering the property of the edge in the frequency domain, a perceptual loss term in the frequency domain is constructed as additional factor. Results show that De-SRGAN can generate deblurred images with low MSE/ MAE, high PSNR/SSIM, high perceptual quality, and high accuracy. This study contributes to improving the accuracy of size measurement due to the deblurred images with sharp and accurate edges.
- 28 May 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (8) , 085022
A de-texturing model for enhancing the accuracy of centroid positioning
In tasks guided by microvision, extracting centroids is a common method for positioning, which is negatively affected by texture. Here, an attention-related de-texturing model is proposed to eliminate the texture of microparts and preserve accurate edges. A network with an attention module called De-texturing Net is built, in which both the transformer and channel attention modules are included. Considering the importance of texture, the additional factor in loss function is constructed based on the Gram matrix difference between target images and generated images. Results show that De-texturing Net can generate de-texturized images with high Peak Signal to Noise Ratio/SSIM, indicating the similarity between de-texturized and target images. Moreover, for the centroid positioning, the error in de-texturized images is significantly lower than the error in original images. This study helps improve the accuracy of centroid positioning due to the de-texturized images with accurate edges.
- 28 May 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (8) , 085022
A de-texturing model for enhancing the accuracy of centroid positioning
In tasks guided by microvision, extracting centroids is a common method for positioning, which is negatively affected by texture. Here, an attention-related de-texturing model is proposed to eliminate the texture of microparts and preserve accurate edges. A network with an attention module called De-texturing Net is built, in which both the transformer and channel attention modules are included. Considering the importance of texture, the additional factor in loss function is constructed based on the Gram matrix difference between target images and generated images. Results show that De-texturing Net can generate de-texturized images with high Peak Signal to Noise Ratio/SSIM, indicating the similarity between de-texturized and target images. Moreover, for the centroid positioning, the error in de-texturized images is significantly lower than the error in original images. This study helps improve the accuracy of centroid positioning due to the de-texturized images with accurate edges.
- 7 March 2023
- Published by Elsevier in Precision Engineering
- Vol. 82, 44-51
Deblurring microscopic image by integrated convolutional neural network
- 7 March 2023
- Published by Elsevier in Precision Engineering
- Vol. 82, 44-51
Deblurring microscopic image by integrated convolutional neural network
- 23 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1
A Generic Algorithm for Position-Orientation Estimation with Microscopic Vision
Position and orientation (PO) estimation with microscopic vision is essential for various micromanipulation tasks. Herein, to improve the accuracy and flexibility of PO estimation, a generic algorithm is proposed based on discriminative correlation filter (DCF), in which a position-estimator and an orientation-estimator are combined into one framework with the developed mutual correction mechanism. The extraction of spectral features is utilized to decouple the rotation and translation transformations of target. And DCF is employed to rapidly estimate the orientation. In addition, the continuous convolution operator is implemented to obtain subgrid resolution in the position-estimator. At last, both the stability and the accuracy of PO estimation are verified. The noise fluctuation in response distribution is effectively restrained to improve the robustness by the mutual correction mechanism. And the introduction of continuous convolution operation can improve the accuracy of position estimation too. The position error of $\sim 1.00~\mu \text{m}$ and the orientation error of ~0.20° are achieved. The comparison and application experiments validate the comprehensive performance of algorithm. Its advantages include the high accuracy, the strong robustness to rotating influence, the universality for various microfeatures.
- 23 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1
A Generic Algorithm for Position-Orientation Estimation with Microscopic Vision
Position and orientation (PO) estimation with microscopic vision is essential for various micromanipulation tasks. Herein, to improve the accuracy and flexibility of PO estimation, a generic algorithm is proposed based on discriminative correlation filter (DCF), in which a position-estimator and an orientation-estimator are combined into one framework with the developed mutual correction mechanism. The extraction of spectral features is utilized to decouple the rotation and translation transformations of target. And DCF is employed to rapidly estimate the orientation. In addition, the continuous convolution operator is implemented to obtain subgrid resolution in the position-estimator. At last, both the stability and the accuracy of PO estimation are verified. The noise fluctuation in response distribution is effectively restrained to improve the robustness by the mutual correction mechanism. And the introduction of continuous convolution operation can improve the accuracy of position estimation too. The position error of $\sim 1.00~\mu \text{m}$ and the orientation error of ~0.20° are achieved. The comparison and application experiments validate the comprehensive performance of algorithm. Its advantages include the high accuracy, the strong robustness to rotating influence, the universality for various microfeatures.