References

The details of the methods used in project-O2 products are described in the following papers or articles.

• Hideaki Goto and Shoichiro Kaneko, ``Synergetic OCR : A Framework for Network-oriented Cooperative OCR Systems,'' Proceedings Image and Vision Computing New Zealand 2004 (IVCNZ 2004), pp.35-40, Nov 2004, Akaroa, New Zealand. [NEW!]
  
  
• Hideaki Goto and Hirotomo Aso, ``Screen Pattern Removal for Character Pattern Extraction from High-resolution Color Document Images,'' Proceedings of 17th International Conference on Pattern Recognition (ICPR2004), Volume 1, pp.490-493, Aug 2004, Cambridge, UK. [NEW!]
  
  
• Hideaki Goto and Hirotomo Aso, ``Character Pattern Extraction from Colorful Documents with Complex Backgrounds,'' Proceedings of 16th International Conference on Pattern Recognition (ICPR2002), Volume III, pp.180-183, Aug 2002. (Québec City, Canada)
  
• Hideaki Goto and Hirotomo Aso, ``Character pattern extraction from documents with complex backgrounds,'' International Journal on Document Analysis and Recognition (IJDAR), Vol.4, No.4, pp.258-268, 2002.
  • Implemented as "dlabel-1.3x".
  
  
• Hideaki Goto and Hirotomo Aso, ``A Character Pattern Extraction Method Applicable to Various Types of Images,'' Proceedings of MVA2000 (IAPR Workshop on Machine Vision Applications), pp.160-163, Nov. 2000.
  • Implemented as "dlabel-1.3x".
  
  
• Hideaki Goto and Hirotomo Aso, "Character Pattern Extraction Based on Local Multilevel Thresholding and Region Growing," Proceedings of 15th International Conference on Pattern Recognition (ICPR2000), Volume 4, pp.430-430, Sept. 2000, Barcelona, Spain.
  • Implemented as "dlabel-1.3x".
  
  
• Hideaki Goto and Hirotomo Aso, "Extracting Curved Text Lines Using Local Linearity of Text Line," International Journal on Document Analysis and Recognition (IJDAR), Vol.2, No.2/3, pp.111-119, 1999.
  • Note: The photographs of the authors were unfortunately swapped by a mistake (probably of the publisher).
  • Sorry, I have no plan to release the program on the Web.
  
  
• Hideaki Goto, Masatsugu Hirayama and Hirotomo Aso, " Character Pattern Extraction from Grayscale Document Images Using Local Multilevel Thresholding," Trans. IEICE (D-II), Vol.J82-D-II, No.11, pp.2188-2192, 1999. (In Japanese)
  • Implemented as "dlabel".
  
  
• Hideaki Goto, Hitoshi Tsukata and Hirotomo Aso, "An algorithm for extracting non-rectangular text blocks from document images," Trans. IEICE (D-II), Vol.J81-D-II, No.1, pp.212-214, 1998. (In Japanese)
  • I'm sorry that this article is written in Japanese. However, figures and equations in the article would help you to understand the algorithm. Please contact Dr.Goto if you need the reprint of this article.
  • We have no plan to release the program on the Web.
  
  
• Hideaki Goto and Hirotomo Aso, "A Framework for Detecting and Selecting Text Line Candidates of Correct Orientation," Proceedings of 14th International Conference on Pattern Recognition (ICPR98), pp.1074-1076, August 1998, Brisbane, Australia.
  • Implemented as "txtori" in O2-dtools package.
  
  
• Hideaki Goto and Hirotomo Aso, "Robust and Fast Text-line Extraction Using Local Linearity of the Text-line," Trans. IEICE (D-II), Vol.J78-D-II, No.3, pp.465-473, March 1995. (In Japanese)
  • Implemented as "lnextr2" in O2-dtools package.
  
  
• Hideaki Goto and Hirotomo Aso, "Robust and Fast Text-line Extraction Using Local Linearity of the Text-line," Systems and Computers in Japan, Vol.26, No.13, pp.21-31, 1995, Scripta Technica, Inc.
  • This is the translated version of the previous paper.
  
  
• Hitoshi Tsukata, Hideaki Goto and Hirotomo Aso, "A method for improving the precision of text line extraction in multi-column documents," 1995 Tohoku-section joint convention record of institutes electrical and information engineers, Japan, 2I21, pp.371.(In Japanese)
  • Implemented as "kiri" in O2-dtools package.
  • The above article is also available on-line here.
    shibu95.ps.gz (303KB, 200dpi scanned bitmap image in PostScript)
  
  
• Hideaki Goto and Hirotomo Aso, "An algorithm for extraction of rules and field-separators in document image," Trans. IEICE (D-II), Vol.J78-D-II, No.12, pp.1935-1939, Dec. 1995. (In Japanese)
  • Implemented as "getlseg".
  • The above paper is also available on-line here.
    ieice95.ps.gz (720KB, 300dpi scanned bitmap image in PostScript)