W
Wei Fan
Researcher at Fujitsu
Publications - 64
Citations - 553
Wei Fan is an academic researcher from Fujitsu. The author has contributed to research in topics: Convolutional neural network & Artificial neural network. The author has an hindex of 9, co-authored 60 publications receiving 481 citations.
Papers
More filters
Proceedings ArticleDOI
Beyond human recognition: A CNN-based framework for handwritten character recognition
TL;DR: In the experiments, the proposed CNN-based handwritten character recognition framework performed even better than human on handwritten digit (MNIST) and Chinese character (CASIA) recognition.
Proceedings ArticleDOI
Handwritten Character Recognition by Alternately Trained Relaxation Convolutional Neural Network
TL;DR: The relaxation convolution layer adopted in the R-CNN, unlike traditional convolutional layer, does not require neurons within a feature map to share the same Convolutional kernel, endowing the neural network with more expressive power.
Patent
Convolutional-neural-network-based classifier and classifying method and training methods for the same
TL;DR: In this paper, a convolutional-neural-network-based classifier is proposed, which consists of a plurality of feature map layers, at least one feature map in each layer, and a plurality-of-convolutional templates corresponding to the plurality of regions.
Proceedings ArticleDOI
Deep Knowledge Training and Heterogeneous CNN for Handwritten Chinese Text Recognition
TL;DR: The experimental results showed that the proposed framework could achieve much better performance than the state-of-the-art methods and can also be applied to other time sequence problems, such as speech recognition and video analysis.
Patent
Convolutional neural network classifier, and classifying method and training method thereof
TL;DR: In this paper, a convolutional neural network (CNN) classifier is proposed, which consists of a plurality of feature image layers and convolution masks, where each convolution mask is used for acquiring response values of nerve cells in the corresponding area.