Offline Handwritten Chinese Character Recognition Based on Improved Googlenet

被引：7

作者：

Min, Feng ^{[1
]}

Zhu, Sicheng ^{[1
]}

Wang, Yansong ^{[1
]}

机构：

[1] Wuhan Inst Technol, Hubei Prov Key Lab Intelligent Robot, Wuhan, Peoples R China

来源：

AIPR 2020: 2020 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION | 2020年

关键词：

GoogLeNet; Chinese character recognition; Convolutional neural network; Inception; Confidence level; ONLINE;

D O I：

10.1145/3430199.3430202

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Aiming at the problem of misrecognition in offline handwritten Chinese character recognition, this paper proposed an improved shallow GoogLeNet and an error elimination algorithm. Compared with the shallow GoogLeNet, the improved shallow GoogLeNet not only reduced the number of training parameters, but also maintained the depth of the Inception structure. According to the error elimination algorithm, the confidence of the samples in the test results was calculated and the erroneous samples in the dataset were removed. Then the dataset was divided into multiple similar character sets and one dissimilar character set. When the recognition result was in the dissimilar character set, it can be used as the final result. Otherwise, the final result could be obtained by the secondary recognition on the corresponding similar character set. The training and testing of the experiment were carried out on the CISIA-HWDB1.1 dataset. The accuracy of the method was 97.48%, which was 6.68% higher than that of the GoogLeNet network.

引用

页码：42 / 46

页数：5

共 50 条

[1] Occluded offline handwritten Chinese character recognition using deep convolutional generative adversarial network and improved GoogLeNet
Li, Jianwu
Song, Ge
Zhang, Minhua
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (09): : 4805 - 4819
[2] Occluded offline handwritten Chinese character recognition using deep convolutional generative adversarial network and improved GoogLeNet
Jianwu Li
Ge Song
Minhua Zhang
Neural Computing and Applications, 2020, 32 : 4805 - 4819
[3] High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps
Zhong, Zhuoyao
Jin, Lianwen
Xie, Zecheng
2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, : 846 - 850
[4] DenseRAN for Offline Handwritten Chinese Character Recognition
Wang, Wenchao
Zhang, Jianshu
Du, Jun
Wang, Zi-Rui
Zhu, Yixing
PROCEEDINGS 2018 16TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2018, : 104 - 109
[5] Research on Offline Handwritten Chinese Character Recognition Based on Deep Learning
Hao, Qiuyun
Wu, Xiaoming
Zhang, Sen
Zhang, Peng
Ma, Xiaofeng
Jiang, Jingsai
2019 9TH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY (ICIST2019), 2019, : 470 - 474
[6] Offline handwritten Chinese character recognition based on DBN fusion model
Liu, Lu
Sun, Weiwei
Ding, Bo
2016 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (ICIA), 2016, : 1807 - 1811
[7] MQDF Discriminative Learning Based Offline Handwritten Chinese Character Recognition
Wang, Yanwei
Ding, Xiaoqing
Liu, Changsong
11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 1100 - 1104
[8] Radical Region based CNN for Offline Handwritten Chinese Character Recognition
Luo, Weike
Kamata, Sei-Ichiro
PROCEEDINGS 2017 4TH IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR), 2017, : 542 - 547
[9] Offline handwritten Chinese character recognition by radical decomposition
Shi, Daming
Damper, Robert I.
Gunn, Steve R.
ACM Transactions on Asian Language Information Processing, 2003, 2 (01): : 27 - 48
[10] The Handwritten Chinese Character Recognition Uses Convolutional Neural Networks with the GoogLeNet
Bi, Ning
Chen, Jiahao
Tan, Jun
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2019, 33 (11)

← 1 2 3 4 5 →