Wenyi Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wenyi Zhou has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Jihong Zhu
College of Physics and Electronic Information, Gannan Normal University, Ganzhou, China
4 shared publications - Haipeng Xiao
College of Physics and Electronic Information, Gannan Normal University, Ganzhou, China
3 shared publications - Lixin Guan
College of Physics and Electronic Information, Gannan Normal University, Ganzhou, China
3 shared publications - Yueyue Fang
College of Physics and Electronic Information, Gannan Normal University, Ganzhou, China
3 shared publications - Junzhe Fu
College of Physics and Electronic Information, Gannan Normal University, Ganzhou, China
2 shared publications - Mengshan Li
College of Physics and Electronic Information, Gannan Normal University, Ganzhou, China
2 shared publications
Latest Publications
- 8 September 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (11) , 519
DCS-Font: dynamic feature enhancement for few-shot font generation
- 8 September 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (11) , 519
DCS-Font: dynamic feature enhancement for few-shot font generation
- 13 March 2026
- Published by Elsevier in Neural Networks
- Vol. 200, 108825
DBML-Font :Double-branch multi-level feature fusion based on diffusion model for few-shot font generation
- 13 March 2026
- Published by Elsevier in Neural Networks
- Vol. 200, 108825
DBML-Font :Double-branch multi-level feature fusion based on diffusion model for few-shot font generation
- 27 November 2025
- Published by Elsevier in Digital Signal Processing
- Vol. 170
Few-shot font generation by frequency feature separation and multi-scale feature aggregation
- 27 November 2025
- Published by Elsevier in Digital Signal Processing
- Vol. 170
Few-shot font generation by frequency feature separation and multi-scale feature aggregation
- Open Access
- 7 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11301
Research on Generalized Hybrid Probability Convolutional Neural Network
This paper first studies the generalization ability of the convolutional layer as a feature mapper (CFM) for extracting image features and the classification ability of the multilayer perception (MLP) in a CNN. Then, a novel generalized hybrid probability convolutional neural network (GHP-CNN) is proposed to solve abstract feature classification with an unknown distribution form. To measure the generalization ability of the CFM, a new index is defined and the positive correlation between it and the CFM is researched. Generally, a fully trained CFM can extract features that are beneficial to classification, regardless of whether the data participate in training the CFM. In the CNN, the fully connected layer in the MLP is not always optimal, and the extracted abstract feature has an unknown distribution. Thus, an improved classifier called the structure-optimized probabilistic neural network (SOPNN) is used for abstract feature classification in the GHP-CNN. In the SOPNN, the separability information is not lost in the normalization process, and the final classification surface is close to the optimal classification surface under the Bayesian criterion. The proposed GHP-CNN utilizes the generalization ability of the CFM and the classification ability of the SOPNN. Experiments show that the proposed network has better classification ability than the existing hybrid neural networks.
- 7 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11301
Open AccessResearch on Generalized Hybrid Probability Convolutional Neural Network
This paper first studies the generalization ability of the convolutional layer as a feature mapper (CFM) for extracting image features and the classification ability of the multilayer perception (MLP) in a CNN. Then, a novel generalized hybrid probability convolutional neural network (GHP-CNN) is proposed to solve abstract feature classification with an unknown distribution form. To measure the generalization ability of the CFM, a new index is defined and the positive correlation between it and the CFM is researched. Generally, a fully trained CFM can extract features that are beneficial to classification, regardless of whether the data participate in training the CFM. In the CNN, the fully connected layer in the MLP is not always optimal, and the extracted abstract feature has an unknown distribution. Thus, an improved classifier called the structure-optimized probabilistic neural network (SOPNN) is used for abstract feature classification in the GHP-CNN. In the SOPNN, the separability information is not lost in the normalization process, and the final classification surface is close to the optimal classification surface under the Bayesian criterion. The proposed GHP-CNN utilizes the generalization ability of the CFM and the classification ability of the SOPNN. Experiments show that the proposed network has better classification ability than the existing hybrid neural networks.