High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps
By Zhuoyao Zhong, Lianwen Jin, Zecheng Xie. IEEE International Conference on Document Analysis and Recognition, 2015
306 citations recorded by the source corpus.
Just like its great success in solving many computer vision problems, the convolutional neural networks (CNN) provided new end-to-end approach to handwritten Chinese character recognition (HCCR) with very promising results in recent years. However, previous CNNs so far proposed for HCCR were neither deep enough nor slim enough. We show in this paper that, a deeper architecture can benefit HCCR a lot to achieve higher performance, meanwhile can be designed with less parameters. We also show that the traditional feature extraction methods, such as Gabor or gradient feature maps, are still useful for enhancing the performance of CNN. We design a streamlined version of GoogLeNet [13], which was original proposed for image classification in recent years with very deep architecture, for HCCR (denoted as HCCR-GoogLeNet). The HCCR-GoogLeNet we used is 19 layers deep but involves with only 7.26 million parameters. Experiments were conducted using the ICDAR 2013 offline HCCR competition dataset. It has been shown that with the proper incorporation with traditional directional feature maps, the proposed single and ensemble HCCR-GoogLeNet models achieve new state of the art recognition accuracy of 96.35% and 96.74%, respectively, outperforming previous best result with significant gap.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/71c5e84597c3e8fefa28429fc1cc0e5771628ec3
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Chenglin Liu
- Jungong Han
- Xu-Yao Zhang
- Fei Yin
- Jianzhuang Liu
- Baochang Zhang
- Luc Van Gool
- Yoshua Bengio
Citations in the corpus
- Gabor Convolutional Networks (2017, methodology): “In [35, 22], Gabor wavelets were used to initialize the deep models or serve as the input layer.”
- Drawing and Recognizing Chinese Characters with Recurrent Neural Network (2016, background): “to the task of offline recognition [9], [10], [11], [12].”