Name
Title | ||
|---|---|---|
DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition |
Abstract | ||
|---|---|---|
Inspired by the theory of Leitner׳s learning box from the field of psychology, we propose DropSample, a new method for training deep convolutional neural networks (DCNNs), and apply it to large-scale online handwritten Chinese character recognition (HCCR). According to the principle of DropSample, each training sample is associated with a quota function that is dynamically adjusted on the basis of the classification confidence given by the DCNN softmax output. After a learning iteration, samples with low confidence will have a higher frequency of being selected as training data; in contrast, well-trained and well-recognized samples with very high confidence will have a lower frequency of being involved in the ongoing training and can be gradually eliminated. As a result, the learning process becomes more efficient as it progresses. Furthermore, we investigate the use of domain-specific knowledge to enhance the performance of DCNN by adding a domain knowledge layer before the traditional CNN. By adopting DropSample together with different types of domain-specific knowledge, the accuracy of HCCR can be improved efficiently. Experiments on the CASIA-OLHDWB 1.0, CASIA-OLHWDB 1.1, and ICDAR 2013 online HCCR competition datasets yield outstanding recognition rates of 97.33%, 97.06%, and 97.51% respectively, all of which are significantly better than the previous best results reported in the literature. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1016/j.patcog.2016.04.007 | Pattern Recognition |
Keywords | Field | DocType |
Convolutional neural network,Deep learning,Handwritten character recognition,Domain-specific knowledge | Neocognitron,Low Confidence,Domain knowledge,Softmax function,Pattern recognition,Character recognition,Convolutional neural network,Computer science,Artificial intelligence,Deep learning,Machine learning,Very High Confidence | Journal |
Volume | Issue | ISSN |
58 | 1 | 0031-3203 |
Citations | PageRank | References |
28 | 0.89 | 44 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weixin Yang | 1 | 105 | 9.16 |
| Lianwen Jin | 2 | 1337 | 113.14 |
| Dacheng Tao | 3 | 19032 | 747.78 |
| zecheng xie | 4 | 96 | 7.55 |
| Ziyong Feng | 5 | 127 | 6.86 |