FONT FINDER: VISUAL RECOGNITION OF TYPEFACE IN PRINTED DOCUMENTS

被引：0
|
作者：
Bui, Tu [1 ]
Collomosse, John [1 ]
机构：
[1] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford GU2 5XH, Surrey, England
来源：
2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2015年
关键词：
Optical Font Recognition (OFR); Typeface Classification; Logistic Regression;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
We describe a novel algorithm for visually identifying the font used in a scanned printed document. Our algorithm requires no pre-recognition of characters in the string (i. e. optical character recognition). Gradient orientation features are collected local the character boundaries, and quantized into a hierarchical Bag of Visual Words representation. Following stop-word analysis, classification via logistic regression (LR) of the codebooked features yields per-character probabilities which are combined across the string to decide the posterior for each font. We achieve 93.4 % accuracy over a 1000 font database of scanned printed text comprising Latin characters.
引用
收藏
页码：3926 / 3930
页数：5
相关论文
共 50 条
  • [11] Typeface identification for printed Chinese characters
    Tseng, YH
    Kuo, CC
    Lee, HJ
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 1998, 12 (02) : 173 - 190
  • [12] Typeface recognition and legibility metrics
    Molinero, Xavier
    Tapias, Montserrat
    Balius, Andreu
    Salvado, Francesc
    COGNITIVE SYSTEMS RESEARCH, 2024, 88
  • [13] A Lightweight Visual Font Style Recognition With Quantized Convolutional Autoencoder
    Tonmoy, Moshiur Rahman
    Rakib, Abdul Fattah
    Rahman, Rashik
    Adnan, Md. Akhtaruzzaman
    Mridha, M. F.
    Huang, Jie
    Shin, Jungpil
    IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY, 2024, 5 : 120 - 130
  • [14] Multi-font recognition of printed Arabic using the BBN Byblos speech recognition system
    LaPre, C
    Zhao, Y
    Raphael, C
    Schwartz, R
    Makhoul, J
    1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 2136 - 2139
  • [15] Convolutional Neural Network for Machine-Printed Traditional Mongolian Font Recognition
    Wei, Hongxi
    Wen, Ya
    Wang, Weiyuan
    Gao, Guanglai
    NEURAL INFORMATION PROCESSING (ICONIP 2018), PT V, 2018, 11305 : 265 - 274
  • [16] Correcting broken characters in the recognition of historical printed documents
    Droettboom, M
    2003 JOINT CONFERENCE ON DIGITAL LIBRARIES, PROCEEDINGS, 2003, : 364 - 366
  • [17] A Comparison of Recognition Strategies for Printed/Handwritten Composite Documents
    Moysset, Bastien
    Messina, Ronaldo
    Kermorvant, Christopher
    2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 158 - 163
  • [18] Survey of Mathematical Expression Recognition for Printed and Handwritten Documents
    Aggarwal, Ridhi
    Pandey, Shilpa
    Tiwari, Anil Kumar
    Harit, Gaurav
    IETE TECHNICAL REVIEW, 2022, 39 (06) : 1245 - 1253
  • [19] Indexing by recognition approach for printed Arabic documents images
    Klaa, Mohamed Amine
    Touj, Soufien
    Ben Amara, Najoua Essoukri
    2008 3RD INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES: FROM THEORY TO APPLICATIONS, VOLS 1-5, 2008, : 534 - +
  • [20] On multiple typeface arabic script recognition
    Zidouri, Abdelmalek
    Research Journal of Applied Sciences, Engineering and Technology, 2010, 2 (05) : 428 - 435
12345