[1]刘露,孙巍巍,丁博. DBN 融合模型对脱机手写汉字识别[J].哈尔滨理工大学学报,2017,(06):82-86.[doi:15938 /j. jhust. 2017. 06. 016]
 LIU Lu,SUN Wei-wei,DING Bo. DBN Fusion Model for Offline HandwrittenChinese Characters Recognition[J].哈尔滨理工大学学报,2017,(06):82-86.[doi:15938 /j. jhust. 2017. 06. 016]
点击复制

 DBN 融合模型对脱机手写汉字识别()
分享到:

《哈尔滨理工大学学报》[ISSN:1007-2683/CN:23-1404/N]

卷:
期数:
2017年06期
页码:
82-86
栏目:
材料科学与工程
出版日期:
2017-12-25

文章信息/Info

Title:
 DBN Fusion Model for Offline Handwritten
Chinese Characters Recognition
文章编号:
1007- 2683( 2017) 06- 0082- 05
作者:
 刘露 孙巍巍 丁博
 ( 哈尔滨理工大学计算机科学与技术学院,黑龙江哈尔滨150080)
Author(s):
 LIU Lu SUN Wei-wei DING Bo
 ( School of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150080,China)
关键词:
脱机手写字 二次判别函数 深度置信网 汉字识别
Keywords:
 offline handwritten character quadratic discriminant function deep belief network Chinesecharacter recognition
分类号:
TP391. 412
DOI:
15938 /j. jhust. 2017. 06. 016
文献标志码:
A
摘要:
 针对脱机手写汉字识别问题,提出一种新的分类器级联识别模型。新模型将修正的二
次判别函数( modified quadratic discriminant function,MQDF) 与深度置信网络( deep belief network,
DBN) 相融合,利用MQDF 先进行识别并得出结果,同时计算一个该识别结果的可信度,通过这个
可信度对识别结果进行判别,若可信度符合要求,则MQDF 的识别结果可作为最终结果直接输出,
否则再与DBN 结合进行二次识别,得到最终的识别结果。实验结果表明,在ETL-9B 手写汉字数据
集上进行的脱机手写汉字识别任务中,使用MQDF 与DBN 融合模型,可以取得比单独使用MQDF
和DBN 更好的准确率
Abstract:
 The requirement of the recognition result is also increasing in practical applications. In this paper,a
new classifier cascade recognition model is proposed for the problem of offline handwritten Chinese character
recognition. New model is the fusion of modified quadratic discriminant function ( MQDF) and deep belief network
( DBN) . First to recognize and get result using MQDF,and calculate the reliability of the recognition result. If the
reliability can meet the requirement,MQDF recognition result can be as the final result directly output. Otherwise
using the DBN to make recognition again and getting the final recognition result. Experiments show that the MQDF
and DBN fusion model proposed in this paper can achieve better accuracy than the single use of MQDF and DBN in
the offline handwritten Chinese character recognition task,which is performed on the ETL-9B handwritten Chinese
character dataset.
更新日期/Last Update: 2018-03-10