Bangla Handwritten Character Recognition using Convolutional Neural Network with Data Augmentation

被引：0
|
作者：
Chowdhury, Rumman Rashid [1 ]
Hossain, Mohammad Shahadat [1 ]
Ul Islam, Raihan [2 ]
Andersson, Karl [2 ]
Hossain, Sazzad [3 ]
机构：
[1] Univ Chittagong, Dept Comp Sci & Engn, Chittagong, Bangladesh
[2] Lulea Univ Technol Skelleftea, Dept Comp Sci Elect & Space Engn, Skelleftea, Sweden
[3] Univ Liberal Arts Bangladesh, Dept Comp Sci & Engn, Dhaka, Bangladesh
来源：
2019 JOINT 8TH INTERNATIONAL CONFERENCE ON INFORMATICS, ELECTRONICS & VISION (ICIEV) AND 2019 3RD INTERNATIONAL CONFERENCE ON IMAGING, VISION & PATTERN RECOGNITION (ICIVPR) WITH INTERNATIONAL CONFERENCE ON ACTIVITY AND BEHAVIOR COMPUTING (ABC) | 2019年
基金：
瑞典研究理事会;
关键词：
Convolutional Neural Network; handwritten character recognition; Bangla handwritten characters; Data augmentation; EXPERT-SYSTEM;
D O I：
10.1109/iciev.2019.8858545
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper proposes a process of Handwritten Character Recognition to recognize and convert images of individual Bangla handwritten characters into electronically editable format, which will create opportunities for further research and can also have various practical applications. The dataset used in this experiment is the BanglaLekha-Isolated dataset [1]. Using Convolutional Neural Network, this model achieves 91.81% accuracy on the alphabets (50 character classes) on the base dataset, and after expanding the number of images to 200,000 using data augmentation, the accuracy achieved on the test set is 95.25%. The model was hosted on a web server for the ease of testing and interaction with the model. Furthermore, a comparison with other machine learning approaches is presented.
引用
收藏
页码：318 / 323
页数：6
相关论文
共 50 条
  • [1] Bangla Handwritten Character Recognition With Multilayer Convolutional Neural Network
    Abir, B. M.
    Mahal, Somania Nur
    Islam, Md Saiful
    Chakrabarty, Amitabha
    [J]. ADVANCES IN DATA AND INFORMATION SCIENCES, ICDIS 2017, VOL 2, 2019, 39 : 155 - 165
  • [2] Isolated Bangla Handwritten Character Recognition with Convolutional Neural Network
    Alif, Mujadded Al Rabbani
    Ahmed, Sabbir
    Hasan, Muhammad Abul
    [J]. 2017 20TH INTERNATIONAL CONFERENCE OF COMPUTER AND INFORMATION TECHNOLOGY (ICCIT), 2017,
  • [3] Bangla Handwritten Basic Character Recognition Using Deep Convolutional Neural Network
    Saha, Chandrika
    Faisal, Rahat Hossain
    Rahman, Md Mostafijur
    [J]. 2019 JOINT 8TH INTERNATIONAL CONFERENCE ON INFORMATICS, ELECTRONICS & VISION (ICIEV) AND 2019 3RD INTERNATIONAL CONFERENCE ON IMAGING, VISION & PATTERN RECOGNITION (ICIVPR) WITH INTERNATIONAL CONFERENCE ON ACTIVITY AND BEHAVIOR COMPUTING (ABC), 2019, : 190 - 195
  • [4] Bangla Handwritten Numeral Recognition using Convolutional Neural Network
    Akhand, M. A. H.
    Rahman, Md. Mahbubar
    Shill, P. C.
    Islam, Shahidul
    Rahman, M. M. Hafizur
    [J]. 2ND INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING AND INFORMATION COMMUNICATION TECHNOLOGY (ICEEICT 2015), 2015,
  • [5] EkushNet: Using Convolutional Neural Network for Bangla Handwritten Recognition
    Rabby, A. K. M. Shahariar Azad
    Haque, Sadeka
    Abujar, Sheikh
    Hossain, Syed Akhter
    [J]. 8TH INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING & COMMUNICATIONS (ICACC-2018), 2018, 143 : 603 - 610
  • [6] Bangla Handwritten Digit Recognition Using Convolutional Neural Network
    Rabby, A. K. M. Shahariar Azad
    Abujar, Sheikh
    Haque, Sadeka
    Hossain, Syed Akhter
    [J]. EMERGING TECHNOLOGIES IN DATA MINING AND INFORMATION SECURITY, IEMIS 2018, VOL 1, 2019, 755 : 111 - 122
  • [7] Bangla-Meitei Mayek scripts handwritten character recognition using Convolutional Neural Network
    Hazra, Abhishek
    Choudhary, Prakash
    Inunganbi, Sanasam
    Adhikari, Mainak
    [J]. APPLIED INTELLIGENCE, 2021, 51 (04) : 2291 - 2311
  • [8] Bangla-Meitei Mayek scripts handwritten character recognition using Convolutional Neural Network
    Abhishek Hazra
    Prakash Choudhary
    Sanasam Inunganbi
    Mainak Adhikari
    [J]. Applied Intelligence, 2021, 51 : 2291 - 2311
  • [9] A two phase trained Convolutional Neural Network for Handwritten Bangla Compound Character Recognition
    Keserwani, Prateek
    Ali, Tofik
    Roy, Partha Pratim
    [J]. 2017 NINTH INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION (ICAPR), 2017, : 70 - 75
  • [10] Handwritten Bangla Numeral Recognition Using Ensembling of Convolutional Neural Network
    Noor, Rouhan
    Islam, Kazi Mejbaul
    Rahimi, Md Jakaria
    [J]. 2018 21ST INTERNATIONAL CONFERENCE OF COMPUTER AND INFORMATION TECHNOLOGY (ICCIT), 2018,
12345