Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model

LI Lanying; ZHOU Zhigang; CHEN Deyun

doi:10.15938/j.jhust.2020.03.021

Chinese

您当前的位置：

首页 >

文章列表页 >

Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model

更新时间：2026-08-31

- Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model
- Vol. 25, Issue 3, Pages: 137-143(2020)
- 作者机构：
  
  哈尔滨理工大学计算机科学与技术学院,哈尔滨,150080
- 作者简介：
- 基金信息：
- DOI：10.15938/j.jhust.2020.03.021
  CLC： TP3914
- Published：2020
- 稿件说明：
移动端阅览
LI Lanying, ZHOU Zhigang, CHEN Deyun. Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model[J]. 2020, 25(3): 137-143.
DOI：

LI Lanying, ZHOU Zhigang, CHEN Deyun. Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model[J]. 2020, 25(3): 137-143. DOI： 10.15938/j.jhust.2020.03.021.

摘要

摘要:针对脱机手写汉字形近字多，提取特征难，识别不准的问题，提出了一种卷积神经网络和深度信念网络的融合模型。首先在数据集上分别训练卷积神经网络和深度信念网络，发现二者的综合TOP-2准确率可达到99.33%。利用卷积神经网络和深度信念网络在图像分析中各自的优势，采用了一种融合比较策略，在两者的TOP-2分类中尽可能准确地取出一个分类结果以提高识别的能力。实验结果表明：卷积神经网络和深度信念网络的融合模型比单独使用卷积神经网络和深度信念网络具有更好的识别效果。

Abstract

Abstract:Aiming at the problem that some offline handwrittenChinese characters are similar in shape and it is difficult to extract thefeature of characters and the recognition is not accurate

a convolutionalneural network and deep belief network fusion model is proposed Firstly

theconvolutional neural network and the deep belief network are trained on thedataset respectively It is found that the comprehensive TOP-2 accuracy of theboth can reach 99.33% Using the advantages of convolutional neural networks anddeep belief networks in image analysis

a fusion comparison strategy is adoptedto extract a classification result as accurately as possible in the TOP-2classification of the two to improve the recognition ability The experimentalresults show that the fusion model of convolutional neural network and deepbelief network has better recognition effect than convolutional neural networkand deep belief network

关键词

Keywords

references

Views

158

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Nodularization Effect Evaluationof Ductile Iron basedon Quick Testing Oxygen Content in Liquid Iron

Fabrication and Mechanical Property of SiC/SiC Composites by Selective Laser Sintering Technology Combined with Precursor Impregnation and Pyrolysis Process

Stability Analysis of a Class of SIR Epidemic Model with Delayed Spontaneous Variation of Virus

Reliability Analysis of ZZ Distribution Under Zero Failure Data

β Property in W hyperbolic Spaces

Related Author

PEI Li-xin

XU Zhen-yu

LI Da-yong

ZENG Tao

ZHOU Yikai

ZHANG Kun

YU Siwen

LI Dong mei

Related Institution

School of Material Science and Engineering，Harbin University of Science and Technology

School of Civil Engineering and Architecture, Harbin University of Science and Technology

School of Material Science and Engineering, Harbin University of Science and Technology

School of Sciences, Harbin University of Science Technology

School of Applied Sciences，Harbin University of Science and Technology

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰