Proceedings ArticleDOI
Deep Knowledge Training and Heterogeneous CNN for Handwritten Chinese Text Recognition
Song Wang,Li Chen,Liang Xu,Wei Fan,Jun Sun,Satoshi Naoi +5 more
- pp 84-89
TLDR
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.Abstract:
It is well known that the handwritten Chinese text recognition is a difficult problem since there are a large number of classes. In order to solve this problem, we proposed a whole new framework for unconstrained handwritten Chinese text recognition. The core module of the framework is the heterogeneous CNN trained by deep knowledge. The experimental results showed that our proposed method could achieve much better performance than the state-of-the-art methods (96.28% vs. 91.39% of CR on CASIA test set). Moreover, since the proposed framework is general, it can also be applied to other time sequence problems, such as speech recognition and video analysis.read more
Citations
More filters
Journal ArticleDOI
Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models
Yichao Wu,Fei Yin,Cheng-Lin Liu +2 more
TL;DR: Evaluating comprehensively neural network language models (NNLMs) and hybrid NNLMs in handwritten Chinese text recognition and replacing the baseline character classifier, over-segmentation, and geometric context models with convolutional neural network (CNN) based models.
Proceedings ArticleDOI
Aggregation Cross-Entropy for Sequence Recognition
TL;DR: Song et al. as mentioned in this paper proposed aggregation cross entropy (ACE) for sequence recognition from a new perspective, which can be directly applied for 2D prediction by flattening the 2D predictions into 1D predictions as the input.
Posted Content
Aggregation Cross-Entropy for Sequence Recognition
TL;DR: This paper proposes a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective, which requires only characters and their numbers in the sequence annotation for supervision, which allows it to advance beyond sequence recognition, e.g., counting problem.
Journal ArticleDOI
Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition
Zi-Rui Wang,Jun Du,Jiaming Wang +2 more
TL;DR: Wang et al. as mentioned in this paper proposed a writer-aware CNN based on parsimonious HMM (WCNN-PHMM), which integrates each convolutional layer with one adaptive layer fed by a writer dependent vector to extract the irrelevant variability in writer information to improve recognition performance.
Proceedings ArticleDOI
A Compact CNN-DBLSTM Based Character Model for Offline Handwriting Recognition with Tucker Decomposition
TL;DR: The results show that using Tucker decomposition alone offers a good solution to building a compact CNN-DBLSTM model which can reduce significantly both the footprint and latency yet without degrading recognition accuracy.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Proceedings ArticleDOI
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
TL;DR: This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.
Proceedings ArticleDOI
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
TL;DR: In this article, the authors show that it is possible to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence.
Proceedings Article
End-to-end text recognition with convolutional neural networks
TL;DR: This paper combines the representational power of large, multilayer neural networks together with recent developments in unsupervised feature learning, which allows them to use a common framework to train highly-accurate text detector and character recognizer modules.