Zhenjie Yang
Research Subjects
Zhenjie Yang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Lei Geng
School of Life Sciences, Tiangong University, Tianjin, China
2 shared publications - Zhitao Xiao
School of Life Sciences, Tiangong University, Tianjin, China
2 shared publications - Fei Yuan
School of Informatics, Xiamen University, Xiamen, China
1 shared publication Hongwei Wu
Xiamen Network Information Security Joint Laboratory, Xiamen, China, 361000
1 shared publication- Jingjing Su
State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, China
1 shared publication - Jun Wu
School of Automation, Wuhan University of Technology, Wuhan 430070, China
1 shared publication
Latest Publications
- Open Access
- 14 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 174922-174930
Face Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks
With the continuous development of deep learning, face detection methods have made the greatest progress. For real-time detection, cascade CNN based on the lightweight model is still the dominant structure that predicts face in a coarse-to-fine manner with strong generalization ability. Compared to other methods, it is not required for a fixed size of the input. However, MTCNN still has poor performance in detecting tiny targets. To improve model generalization ability, we propose a Receptive Field Enhanced Multi-Task Cascaded CNN. This network takes advantage of the Inception-V2 block and receptive field block to enhance the feature discriminability and robustness for small targets. The experimental results show that the performance of our network is improved by 1.08% on the AFW, 2.84% on the PASCAL FACE, 1.31% on the FDDB, and 2.3%, 2.1%, and 6.6% on the three sub-datasets of the WIDER FACE benchmark in comparison with MTCNN respectively. Furthermore, our structure uses 16% fewer parameters.
- 14 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 174922-174930
Open AccessFace Detection Based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks
With the continuous development of deep learning, face detection methods have made the greatest progress. For real-time detection, cascade CNN based on the lightweight model is still the dominant structure that predicts face in a coarse-to-fine manner with strong generalization ability. Compared to other methods, it is not required for a fixed size of the input. However, MTCNN still has poor performance in detecting tiny targets. To improve model generalization ability, we propose a Receptive Field Enhanced Multi-Task Cascaded CNN. This network takes advantage of the Inception-V2 block and receptive field block to enhance the feature discriminability and robustness for small targets. The experimental results show that the performance of our network is improved by 1.08% on the AFW, 2.84% on the PASCAL FACE, 1.31% on the FDDB, and 2.3%, 2.1%, and 6.6% on the three sub-datasets of the WIDER FACE benchmark in comparison with MTCNN respectively. Furthermore, our structure uses 16% fewer parameters.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 281-286
Fast Traffic Sign Recognition Based on Convolution Neural Network
Due to the uncontrollable conditions and poses of traffic signs, Traffic Sign Recognition (TSR) has been challenging the robustness and efficiency of the existing algorithm. In this work, a method of fast traffic sign recognition based convolutional neural networks (FTSR-CNN) is proposed. A new architecture of convolution neural network is designed, which extracts feature using convolution kernels by sliding filter, and reduces dimension by pooling. In forward propagation, the loss of the whole network is computed. Then stochastic gradient descent method is exploited to minimize loss in step of back propagation. The parameters and activation function of the network are adjusted to optimize the performance. Finally, the full connection is utilized to classify the traffic signs. Affine transformation increases diversity of training samples, which can enhance the adaptability. The proposed method has been evaluated on German Traffic Sign Recognition Benchmark and Tsinghua-Tencent 100K datasets. Experiments demonstrate that it is sufficient to attain high classification accuracy and ensure the efficiency.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 281-286
Fast Traffic Sign Recognition Based on Convolution Neural Network
Due to the uncontrollable conditions and poses of traffic signs, Traffic Sign Recognition (TSR) has been challenging the robustness and efficiency of the existing algorithm. In this work, a method of fast traffic sign recognition based convolutional neural networks (FTSR-CNN) is proposed. A new architecture of convolution neural network is designed, which extracts feature using convolution kernels by sliding filter, and reduces dimension by pooling. In forward propagation, the loss of the whole network is computed. Then stochastic gradient descent method is exploited to minimize loss in step of back propagation. The parameters and activation function of the network are adjusted to optimize the performance. Finally, the full connection is utilized to classify the traffic signs. Affine transformation increases diversity of training samples, which can enhance the adaptability. The proposed method has been evaluated on German Traffic Sign Recognition Benchmark and Tsinghua-Tencent 100K datasets. Experiments demonstrate that it is sufficient to attain high classification accuracy and ensure the efficiency.
- Open Access
- 4 August 2015
- Published by Springer Nature
- p. 68-79
Phase Unwrapping Method Based on Heterodyne Three Frequency Non-equal Step Phase Shift
- 4 August 2015
- Published by Springer Nature
- p. 68-79
Open AccessPhase Unwrapping Method Based on Heterodyne Three Frequency Non-equal Step Phase Shift