L
Li Chen
Researcher at Fujitsu
Publications - 14
Citations - 227
Li Chen is an academic researcher from Fujitsu. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has an hindex of 6, co-authored 14 publications receiving 187 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
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
Training method and apparatus for neutral network for image recognition
TL;DR: In this article, a training method and a training apparatus for a neutral network for image recognition is provided, where a sample image is represented as a point set in a high-dimensional space.
Book ChapterDOI
Adaptive Local Receptive Field Convolutional Neural Networks for Handwritten Chinese Character Recognition
TL;DR: This work argues that the best way to select optimal local receptive field is to let CNNs learn how to choose it, and uses different sizes of local receptive fields to produce several sets of feature maps, then an element-wise max pooling layer is introduced.
Proceedings ArticleDOI
Reconstruction combined training for convolutional neural networks on character recognition
TL;DR: This paper has proposed a novel CNN model with two training feedbacks: the reconstruction feedback and the classification feedback that can outperform those state-of-the-art improved CNN models, which is proved by the experimental results.