Font Recognition for Persian Optical Character Recognition System

被引：0
|
作者：
Eghbali, Koorosh [1 ]
Veisi, Hadi [1 ]
Mirzaie, Mohsen [1 ]
Behbahani, Yasser Mohseni [2 ]
机构：
[1] Univ Tehran, Fac New Sci & Technol, Tehran, Iran
[2] Sharif Univ Technol, Speech Proc Lab, Tehran, Iran
来源：
2017 10TH IRANIAN CONFERENCE ON MACHINE VISION AND IMAGE PROCESSING (MVIP) | 2017年
关键词：
Font recognition; Persian OCR; Random forest; Nerual network; Gabor filter; PCA;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Font recognition is one of the preprocessing steps in optical character recognition (OCR) systems that affects on their performance. In this paper two methods are proposed for Persian font recognition. In the first method, Gabor filter is used for feature extraction from the images, then principle component analysis (PCA) applied to reduce feature dimensions and finally, a multi-layer Perceptron (MLP) neural network is used for the classification. In the second techniques, random forest is utilized for recognizing fonts. For evaluation, a dataset includes 10 popular Persian fonts is used. The proposed Gabor-PCA-MLP method has achieved 98.70% of F-measure, and random forest resulted in of 96.95% of F-measure.
引用
收藏
页码：252 / 257
页数：6
相关论文
共 50 条
  • [1] Optical Character Recognition System for Urdu Words in Nastaliq Font
    Shabbir, Safia
    Siddiqi, Imran
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2016, 7 (05) : 567 - 576
  • [2] Optical font recognition of single chinese character
    Chen, L
    Ding, XQ
    [J]. DOCUMENT RECOGNITION AND RETRIEVAL X, 2003, 5010 : 219 - 226
  • [3] Individual character font recognition based on guidance font
    Miao, XF
    Tian, XD
    Guo, BL
    [J]. 2002 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-4, PROCEEDINGS, 2002, : 1715 - 1717
  • [4] Support Vector Machine for Persian Font Recognition
    Borji, A.
    Hamidi, M.
    [J]. PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 22, 2007, 22 : 10 - +
  • [5] Semi-supervised Persian font recognition
    Imani, Maryam Bahojb
    Keyvanpour, Mohamad Reza
    Azmi, Reza
    [J]. WORLD CONFERENCE ON INFORMATION TECHNOLOGY (WCIT-2010), 2011, 3
  • [6] Character independent font recognition on a single Chinese character
    Ding, Xiaoqing
    Chen, Li
    Wu, Tao
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2007, 29 (02) : 195 - 204
  • [7] Recognition-based Segmentation in Persian Character Recognition
    Zand, Mohsen
    Nilchi, Ahmadreza Naghsh
    Monadjemi, S. Amirhassan
    [J]. PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 28, 2008, 28 : 183 - 187
  • [8] OPTICAL CHARACTER-RECOGNITION SYSTEM
    HAMILTON, WB
    [J]. DATA PROCESSING, 1962, 4 (07): : 22 - 26
  • [9] OMNI-FONT OPTICAL CHARACTER-RECOGNITION (OCR) - A UNIQUE, AUTOMATED TEXT ENTRY SYSTEM
    DERFALL, A
    [J]. ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 1982, 183 (MAR): : 27 - CINF
  • [10] A recognition-based Arabic optical character recognition system
    Cheung, A
    Bennamoun, M
    Bergmann, NW
    [J]. 1998 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5, 1998, : 4189 - 4194
12345