Handwritten Chinese Character Recognition With Spatial Transformer And Deep Residual Networks
2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2016)
摘要
This paper considers using deep neural networks for handwritten Chinese character recognition (HCCR) with arbitrary position, scale, and orientations. To solve this problem, we combine the recently proposed spatial transformer network (STN) with the deep residual network (DRN). The STN acts like a character shape normalization procedure. Different from the traditional heuristic shape normalization methods, STN is learned directly from the data. Furthermore, the DRN makes the training of very deep network to be both efficient and effective. With the combination of STN and DRN, the whole model can be trained jointly in an end-to-end manner. In this paper, new state-of-the-art performance has been achieved by our proposed model on the offline ICDAR-2013 Chinese handwriting competition database. Moreover, the experiment on randomly distorted samples shows that the STN is very effective for robust HCCR in rectifying the shape of distorted characters.
更多查看译文
关键词
distorted characters,DRN,STN,spatial transformer network,HCCR,deep residual networks,handwritten Chinese character recognition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络