RECOGNITION OF MACHINE PRINTED BROKEN ORIYA CHARACTERS USING SIFT FEATURES

被引：1
|
作者：
Sharma, Sandeepika [1 ]
Choudhray, Sneha [2 ]
Kumar, Bhupendra [3 ]
机构：
[1] IGDTUW, Delhi, India
[2] CDAC Noida, Hyderabad, Telangana, India
[3] CDAC Noida, STO, Hyderabad, Telangana, India
来源：
6TH INTERNATIONAL CONFERENCE ON COMPUTER & COMMUNICATION TECHNOLOGY (ICCCT-2015) | 2015年
关键词：
OCR; Broken Characters; SIFT;
D O I：
10.1145/2818567.2818587
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
OCR for Indian scripts has been an active area of research for years. The fine printed documents can be recognized easily but the technology underperforms in case of degraded document images. In this paper a gradient based feature extraction technique is presented to recognize the broken printed Oriya characters. Scale Invariant Feature Transform (SIFT) key point descriptors are used as the feature set to represent each character sample at the feature space and a Brute-Force Matcher interface is used as a classifier to classify the character images. On the basis of the SIFT feature set the recognition rate was found to be 82.7%
引用
收藏
页码：106 / 109
页数：4
相关论文
共 50 条
  • [21] Recognition of machine printed Arabic characters and numerals based on MCR
    Zidouri, ABC
    Chinveeraphan, S
    Sato, M
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1995, E78D (12): : 1649 - 1655
  • [22] Automatic Recognition of Railway Signs Using SIFT Features
    Nassu, Bogdan Tomoyuki
    Ukai, Masato
    [J]. 2010 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2010, : 348 - 354
  • [23] The CNN Based Machine-printed Traditional Mongolian Characters Recognition
    Hu, Hongwei
    Wei, Hongxi
    Liu, Zhenyu
    [J]. PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 3937 - 3941
  • [24] Pairwise coupling for machine recognition of hand-printed Japanese characters
    Roth, V
    Tsuda, K
    [J]. 2001 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2001, : 1120 - 1125
  • [25] Recognition of printed Chinese characters by using neural network
    Khawaja, Attaullah
    Tingzhi, Shen
    Memon, Noor Mohammad
    Rajpar, Altaf
    [J]. 10TH IEEE INTERNATIONAL MULTITOPIC CONFERENCE 2006, PROCEEDINGS, 2006, : 169 - +
  • [26] RECOGNITION OF PRINTED THAI CHARACTERS USING A MATCHING METHOD
    KIMPAN, C
    ITOH, A
    KAWANISHI, K
    [J]. IEE PROCEEDINGS-E COMPUTERS AND DIGITAL TECHNIQUES, 1983, 130 (06): : 183 - 188
  • [27] SIFT Features for Face Recognition
    Geng, Cong
    Jiang, Xudong
    [J]. 2009 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, VOL 1, 2009, : 598 - 602
  • [28] Recognition of Oriya and English Languages Based on LBP Features
    Manjula, S.
    Hegadi, Ravindra S.
    [J]. PROCEEDINGS OF THE 2017 IEEE SECOND INTERNATIONAL CONFERENCE ON ELECTRICAL, COMPUTER AND COMMUNICATION TECHNOLOGIES (ICECCT), 2017,
  • [29] RECOGNITION OF PRINTED CHINESE CHARACTERS
    CASEY, R
    NAGY, G
    [J]. IEEE TRANSACTIONS ON ELECTRONIC COMPUTERS, 1966, EC15 (01): : 91 - &
  • [30] Farsi/Arabic Optical Font Recognition Using SIFT Features
    Zahedi, Morteza
    Eslami, Saeideh
    [J]. WORLD CONFERENCE ON INFORMATION TECHNOLOGY (WCIT-2010), 2011, 3
12345