Separation of Overlapping and Touching Lines within Handwritten Arabic Documents

被引：0
|
作者：
Ouwayed, Nazih [1 ]
Belaid, Abdel [1 ]
机构：
[1] Univ Nancy 2, LORIA, Vandoeuvre Les Nancy, France
来源：
COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS | 2009年 / 5702卷
关键词：
Handwriting line segmentation; Arabic documents; Overlapping and Touching lines; Calligraph morphology;
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：
In this paper, the propose all approach for the separation of overlapping and touching lines within handwritten Arabic documents. Our approach is based on the morphology analysis of the terminal letters of Arabic words. Starting from 4 categories of possible endings, the else the angular variance to follow the connection and separate the endings. The proposed separation scheme has been evaluated on 100 documents contains 640 overlapping and touching occurrences reaching all accuracy of about 96.88%.
引用
收藏
页码：237 / 244
页数：8
相关论文
共 50 条
  • [41] Word Stretching for Effective Segmentation and Classification of Historical Arabic Handwritten Documents
    Al Aghbari, Zaher
    Brook, Salama
    RCIS 2009: PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON RESEARCH CHALLENGES IN INFORMATION SCIENCE, 2009, : 217 - 224
  • [42] ON SEGMENTATION OF TOUCHING CHARACTERS AND OVERLAPPING LINES IN DEGRADED PRINTED GURMUKHI SCRIPT
    Jindal, Manish Kumar
    Lehal, Gurpreet Singh
    Sharma, Rajendra Kumar
    INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS, 2009, 9 (03) : 321 - 353
  • [43] A segmentation method for touching Japanese handwritten characters based on connecting condition of lines
    Yamaguchi, T
    Yoshikawa, T
    Shinogi, T
    Tsuruoka, S
    Teramoto, M
    SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 837 - 841
  • [44] Separation of single-touching handwritten numeral strings based on structural features
    Yu, DG
    Yan, H
    PATTERN RECOGNITION, 1998, 31 (12) : 1835 - 1847
  • [45] Segmentation of Historical Handwritten Documents into Text Zones and Text Lines
    Gatos, Basilis
    Louloudis, Georgios
    Stamatopoulos, Nikolaos
    2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 464 - 469
  • [46] Multi-Oriented Text Line Extraction from Handwritten Arabic Documents
    Ouwayed, Nazih
    Belaid, Abdel
    PROCEEDINGS OF THE 8TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS, 2008, : 339 - 346
  • [47] Segmentation of Merged Lines and Script Identification in Handwritten Bilingual Documents
    Zinjore, Ranjana S.
    Ramteke, R. J.
    Pathak, Varsha M.
    PROCEEDINGS OF THE 9TH ANNUAL MEETING OF THE FORUM FOR INFORMATION RETRIEVAL EVALUATION (FIRE 2017), 2017, : 29 - 32
  • [48] HAH manuscripts: A holistic paradigm for classifying and retrieving historical Arabic handwritten documents
    Al Aghbari, Zaher
    Brook, Salama
    EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (08) : 10942 - 10951
  • [49] Deep Learning-Based Segmentation of Connected Components in Arabic Handwritten Documents
    Gader, Takwa Ben Aïcha
    Echi, Afef Kacem
    Communications in Computer and Information Science, 2022, 1589 CCIS : 93 - 106
  • [50] End-to-End Machine Learning Solution for Recognizing Handwritten Arabic Documents
    Shtaiwi, Reem E.
    Abandah, Gheith A.
    Sawalhah, Safaa A.
    2022 13TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION SYSTEMS (ICICS), 2022, : 180 - 185
12345