Research on social security card number identification method based on the deep belief network

YANG Tao; ZHANG Yun-wei; YANG Rui

doi:10.13873/J.1000-9787(2017)08-0059-03

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on social security card number identification method based on the deep belief network

更新时间：2025-09-11

- Research on social security card number identification method based on the deep belief network
- Vol. 36, Issue 8, Pages: 59-61+68(2017)
- 作者机构：
  
  昆明理工大学信息工程与自动化学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2017)08-0059-03
  CLC： TP391.41
- Published：2017
- 稿件说明：
移动端阅览
[1]杨涛,张云伟,杨瑞.基于深度信念网络的社保卡号码识别方法[J].传感器与微系统,2017,36(08):59-61+68.

YANG Tao, ZHANG Yun-wei, YANG Rui. Research on social security card number identification method based on the deep belief network[J]. 2017, 36(8): 59-61+68.
[1]杨涛,张云伟,杨瑞.基于深度信念网络的社保卡号码识别方法[J].传感器与微系统,2017,36(08):59-61+68. DOI： 10.13873/J.1000-9787(2017)08-0059-03.

YANG Tao, ZHANG Yun-wei, YANG Rui. Research on social security card number identification method based on the deep belief network[J]. 2017, 36(8): 59-61+68. DOI： 10.13873/J.1000-9787(2017)08-0059-03.

摘要

提出了一种基于深度信念网络（DBN）的社保卡号码识别方法

通过采集社保卡图像

采用模块分割的方法

对社保卡号码区域进行行分割

利用区域生长的方法对行内号码分割

将号码图像灰度化与二值化

并归一化为32×32大小

作为深度信念网络的输入数据

训练3层受限玻尔兹曼机（RBM）来获得更加抽象的特征表达

模型的最顶层结合Softmax回归分类器对抽取后的特征进行分类。实验结果表明:其准确率高达98.3%

与BP神经网络和支持向量机（SVM）模型相比

深度信念网络学习了数据的高层特征的同时降低了特征维数

提高了分类器的分类精度

有效提高了社保卡号码识别率。

Abstract

A method based on deep belief networks（ DBN） is proposed to identify social security card number.Firstly

collect the social security card image and segment the card number area by the module segmentation.Secondly

split a single character of the card number using the regional growth method. Thirdly

the character image is grayed

binarized and normalized to the size of 32 × 32

which is taking as the input data of DBN.Training the 3 layers restricted Boltzmann machine（ RBM） to obtain more abstract features. The top layer of the model combined the softmax regression classifier to classify the extracted features. Experimental results show that the accuracy rate is up to 98. 3%. Compared with the BP neural network and support vector machine（ SVM）model

the DBN not only learned the high-level characteristics but also reduced the dimension of features and improved the accuracy of classifier classification. Finally

it effectively improved the recognition rate of social security card number.

关键词

Keywords

references

深度信念网络在故障指示器检测中的应用 [J]. 阳武,李倩,赵继生,高强,余萍. 传感器与微系统 . 2015(07)

基于结构特征的纸币号码识别方法 [J]. 苑玮琦,金灿. 计算机工程与应用 . 2014(08)

模板匹配技术在图像识别中的应用 [J]. 田娟,郑郁正. 传感器与微系统 . 2008(01)

基于并行特征组合与广义K-L变换的字符识别 [J]. 杨健,杨静宇,高建贞. 软件学报 . 2003(03)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Face recognition algorithm based on Gabor feature and DBN

Related Author

YANG Rui

ZHANG Yun-wei

GOU Shuang

ZHI Yan-li

Related Institution

School of Information Engineering and Automation,Kunming University of Science and Technology

⁰