Text-Color-Independent Binarization for Degraded Document Image Based on MAP-MRF Approach

• ORII Hideaki

  Graduate School of Engineering, Kyushu Institute of Technology

• KAWANO Hideaki

  Faculty of Engineering, Kyushu Institute of Technology

• MAEDA Hiroshi

  Faculty of Engineering, Kyushu Institute of Technology

• IKOMA Norikazu

  Faculty of Engineering, Kyushu Institute of Technology

抄録

We propose a novel background and foreground estimation algorithm in MAP-MRF approach for binarization of degraded document image. In the proposed algorithm, an assumption that background whiteness and foreground blackness is not employed differently from the conventional algorithm, and we employ character's irregularities based on local statistics. This makes the method possible to apply to the image with various colored characters, ex. outlined characters by colored background. The effectiveness and the validity are shown by applying the proposed method to various degraded document images.

収録刊行物

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E94-A (11), 2342-2349, 2011

  一般社団法人 電子情報通信学会

キーワード

• binarization
• graph cut
• character extraction

詳細情報

• CRID: 1390282681288723712
• NII論文ID: 10030191989
• NII書誌ID: AA10826239
• DOI: 10.1587/transfun.e94.a.2342
• ISSN: 17451337
• ISSN: 09168508
• Web Site: http://www.jstage.jst.go.jp/article/transfun/E94.A/11/E94.A_11_2342/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可