Devanagari Character Recognition in Scene Images

被引:2
|
作者
Narang, Vipin [1 ,2 ]
Roy, Sujoy [2 ]
Murthy, O. V. R. [3 ]
Hanmandlu, M. [3 ]
机构
[1] ASTAR, Singapore Immunol Network, Singapore, Singapore
[2] ASTAR, Inst Infocomm Res, Singapore, Singapore
[3] IIT Delhi, Dept Elect Engn, Delhi, India
关键词
Devanagari characters; Part-based model; Object recognition; camera-based character recognition;
D O I
10.1109/ICDAR.2013.184
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Character recognition in scene images is an extremely challenging task. Although several techniques are reported performing well, they pertain to English only. This paper focuses on Devanagari character recognition from scene images. Devanagari script is very popular language and has very typical characteristics different from other scripts, particularly English. Combination of basic Devanagari consonants and vowels in multi-variegated ways can yield as many as 100s of characters. Building a classifier to recognize all these classes will be a difficult task. To alleviate this problem, a novel part-based model technique is proposed. 40 basic classes were identified from the Devanagari script for the same purpose. The technique was proposed so as to classify an instance of one these classes in any given test sample. Procuring a large dataset for training is not feasible in the case of scene images. To simultaneously solve this problem, we developed our technique that can use either the machine printed or the handwritten dataset for training. We present our results on the publicly available dataset (DSIW2K) containing images of street scenes taken in New Delhi, India.
引用
收藏
页码:902 / 906
页数:5
相关论文
共 50 条
  • [1] Character Recognition in Natural Scene Images
    Akbani, O.
    Gokrani, A.
    Quresh, M.
    Khan, Furqan M.
    Behlim, Sadaf I.
    Syed, Tahir Q.
    [J]. 2015 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES (ICICT), 2015,
  • [2] A Character Recognition Method in Natural Scene Images
    Gonzalez, Alvaro
    Bergasa, Luis M.
    Javier Yebes, J.
    Bronte, Sebastian
    [J]. 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 621 - 624
  • [3] Character extraction and recognition in natural scene images
    Wang, XW
    Ding, XQ
    Liu, CS
    [J]. SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 1084 - 1088
  • [4] Word Spotting in Scene Images based on Character Recognition
    Bazazian, Dena
    Karatzas, Dimosthenis
    Bagdanov, Andrew D.
    [J]. PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 1953 - 1955
  • [5] Optimizing Character Class Count for Devanagari Optical Character Recognition
    Singh, Jasbir
    Lehal, Gurpreet Singh
    [J]. INFORMATION SYSTEMS FOR INDIAN LANGUAGES, 2011, 139 : 144 - 149
  • [6] Devanagari Character Recognition: A Comprehensive Literature Review
    Arora, Sandhya
    Malik, Latesh
    Goyal, Sonakshi
    Bhattacharjee, Debotosh
    Nasipuri, Mita
    Krejcar, Ondrej
    [J]. IEEE Access, 2025, 13 : 1249 - 1284
  • [7] On the Performance Improvement of Devanagari Handwritten Character Recognition
    Singh, Pratibha
    Verma, Ajay
    Chaudhari, Narendra S.
    [J]. APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2015, 2015
  • [8] Devanagari Text Extraction from Natural Scene Images
    Raj, Hrishav
    Ghosh, Rajib
    [J]. 2014 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), 2014, : 513 - 517
  • [9] Character Recognition in Natural Scene Images Using Local Description
    Zhang, Boyu
    Zhao, Wei
    Liu, JiaFeng
    Wu, Rui
    Tang, XiangLong
    [J]. INTELLIGENT SCIENCE AND INTELLIGENT DATA ENGINEERING, ISCIDE 2011, 2012, 7202 : 193 - 200
  • [10] Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam
    Mathew, Minesh
    Jain, Mohit
    Jawahar, C. V.
    [J]. 2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2017), VOL 7, 2017, : 42 - 46