Offline Printed Tai Le Character Recognition Using VGGNET

被引：1
|
作者：
Zhao, Jingying [1 ,2 ]
Guo, Hai [1 ]
Song, Yifan [1 ]
Dai, Ling [1 ]
Liu, Yifan [1 ]
机构：
[1] Dalian Minzu Univ, Coll Comp Sci & Engn, Dalian, Peoples R China
[2] Dalian Univ Technol, Fac Elect Informat & Elect Engn, Dalian, Peoples R China
来源：
2021 IEEE INTERNATIONAL CONFERENCE ON INFORMATION COMMUNICATION AND SOFTWARE ENGINEERING (ICICSE 2021) | 2021年
关键词：
Tai Le; optical character recognition; image digital processing; VGGNET;
D O I：
10.1109/ICICSE52190.2021.9404133
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
It is a difficult problem to recognize the Tai Le characters, since they are close in shape and high in proportion. This paper constructs an offline printed Tai Le recognition model based on VGGNET. First, the database YDH2019.1 containing 135000 printed Tai Le character images and 35 types of Tai Le characters is built. Then, YDH2019.1 is preprocessed by noise reduction and normalization, and VGG16 is used as the classifier of the model. The results show that the Precision of the recognition model is 0.999943, recall is 0.999943, and fl-score is 0.999943, which can effectively recognize the offline printed Tai Le characters.
引用
收藏
页码：117 / 121
页数：5
相关论文
共 50 条
  • [41] Writer Identification for Offline Handwritten Kanji without using Character Recognition Features
    Soma, Ayumu
    Arai, Masayuki
    PROCEEDINGS OF THE 2013 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY APPLICATIONS (ICISTA-2013), 2013, 58 : 96 - 98
  • [42] Offline handwritten Devanagari modified character recognition using convolutional neural network
    Bisht, Mamta
    Gupta, Richa
    SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2021, 46 (01):
  • [43] UrduDeepNet: offline handwritten Urdu character recognition using deep neural network
    Faisel Mushtaq
    Muzafar Mehraj Misgar
    Munish Kumar
    Surinder Singh Khurana
    Neural Computing and Applications, 2021, 33 : 15229 - 15252
  • [44] Offline Handwritten Chinese Character Recognition Using Genetic Algorithm and Rough Set
    Tian Jipeng
    Liu Weiguang
    Wang Hailong
    2014 IEEE 7TH JOINT INTERNATIONAL INFORMATION TECHNOLOGY AND ARTIFICIAL INTELLIGENCE CONFERENCE (ITAIC), 2014, : 74 - 78
  • [45] Odia Offline Typewritten Character Recognition using Template Matchingwith Unicode Mapping
    Panda, Smruti Rekha
    Tripathy, Jogeswar
    2015 International Symposium on Advanced Computing and Communication (ISACC), 2015, : 109 - 115
  • [46] Study on printed Tibetan character recognition
    Engineering Research Center of Tibetan Information Technology, Ministry of Education, Tibet University, Lhasa, Tibet, China
    不详
    Proc. - Int. Conf. Artif. Intell. Comput. Intell., AICI, (280-285):
  • [47] A database for Arabic printed character recognition
    AbdeRaouf, Ashraf
    Higgins, Colin A.
    Khalil, Mahmoud
    IMAGE ANALYSIS AND RECOGNITION, PROCEEDINGS, 2008, 5112 : 567 - +
  • [48] HAND-PRINTED CHARACTER RECOGNITION
    MUNSON, JH
    DATAMATION, 1968, 14 (11): : 123 - &
  • [49] Printed Thai Character Segmentation and Recognition
    Chomphuwiset, Phatthanaphong
    2017 IEEE 4TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE (ISCMI), 2017, : 123 - 127
  • [50] Study on printed Tibetan character recognition
    Wang, Weilan
    Ding, Xiaoqing
    Chen, Li
    Wang, Hua
    Jisuanji Gongcheng/Computer Engineering, 2003, 29 (03):
12345