Skip to main content
SpringerLink
Log in

Methods and strategies on off-line cursive touched characters segmentation: a directional review

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

Character segmentation is a challenging problem in the field of optical character recognition. Presence of touched characters make this dilemma more crucial. The goal of this paper is to provide major concepts and progress in domain of off-line cursive touched character segmentation. Accordingly, two broad classes of technique are identified. These include methods that perform explicit or implicit character segmentation. The basic methods used by each class of technique are presented and the contributions of individual algorithms within each class are discussed. It is the first survey that focuses on touched character segmentation and provides segmentation rates, descriptions of the test data for the approaches discussed. Finally, the main trends in the field of touched character segmentation are examined, important contributions are presented and future directions are also suggested.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Alhajj R, Polat F, Elnagar A (2000) Employing multi-agents to identify touching of adjacent digits in handwritten Hindi numerals. In: Proceedings of the IEEE international conference on systems, man, and cybernetics, vol 4. pp 2725–2730

  • Bae JH, Jung KC, Kim JW, Kim HJ (1998) Segmentation of touching characters using an MLP. Pattern Recognit Lett 19: 701–709

    Article  MATH  Google Scholar 

  • Bansal V, Sinha RMK (2002) Segmentation of touching and fused Devanagari characters. Pattern Recognit 35(4): 875–893

    Article  MATH  Google Scholar 

  • Bayer T, Kressel U (1993) Cut classification for segmentation. Paper presented at the proceedings of international conference on document analysis and recognition. Tsukuba Science City, Japan, pp 565–568

  • Broumandnia A, Shanbehzadeh J, Nourani M (2007) Segmentation of printed Farsi/Arabic words. In: Proceedings of IEEE/ACS international conference on computer systems and applications. pp 761–766

  • Casey RG, Lecolinet E (1996) A survey of methods and strategies in character segmentation. IEEE Trans Pattern Anal Mach Intell 17: 690–706

    Article  Google Scholar 

  • Casey RG, Nagy G (1982) Recursive segmentation and classification of composite character patterns. Paper presented at the proceedings of the 6th international conference on pattern recognition, Munich, Germany

  • Chunheng W, Hotta Y, Suwa M, Naoi N (2004) Handwritten Chinese address recognition. In: Proceedings of the ninth international workshop on frontiers in handwriting recognition. pp 539–544

  • Dijkstra EW (1959) A note on two problems in connection with graphs. Numer Comput Math 1: 269–271

    Article  MATH  MathSciNet  Google Scholar 

  • Elnagar A, Alhajj R (2003) Segmentation of connected handwritten numeral strings. Pattern Recognit 36(3): 625–634

    Article  Google Scholar 

  • Fujisawa H (2007) A view on the past and future of character and document recognition. In: Ninth international conference on document analysis and recognition. pp 3–7

  • Garain U, Chaudhuri BB (2002) Segmentation of touching characters in printed devnagari and bangla scripts using fuzzy multifactorial analysis. IEEE Trans Syst Man Cybern 32(4): 449–459

    Article  Google Scholar 

  • Han Z, Liu CP, Yin XC (2005) A two-stage handwritten character segmentation approach in mail address recognition. In: Proceedings of eighth international conference on document analysis and recognition, vol 1. pp 111–115

  • Hilditch CJ (1969) Linear skelton from square cupboards. Mach Intell 4: 403–420

    Google Scholar 

  • Hoffman RL, Mccullough JW (1971) Segmentation methods for recognition of machine-printed characters. IBM J Res Dev 15, 153–165

    Article  Google Scholar 

  • Hong-Gang Z, Gang L, Wei-Ran X, Jun G (2002) An algorithm of handwritten digits segmentation based on multi-mould. In: Proceedings of international conference on machine learning and cybernetics, vol 2. pp 1081–1084

  • Jayarathna UKS, Bandara GEMDC (2006) New segmentation algorithm for off-line handwritten connected character segmentation. In: Proceedings of the first international conference on industrial and information systems. pp 540–546

  • Jianming H, Donggang Y, Hong Y (1999) Construction of partitioning paths for touching handwritten characters. Non-Linear Anal 20(3): 293–303

    MATH  Google Scholar 

  • Jin-Hak B, Kee-Chul J, Jin-Wook K, Hang-Joon K (1998) Segmentation of touching characters using an MLP. Pattern Recognit Lett 19(8): 701–709

    Article  MATH  Google Scholar 

  • Jiqiang S, Zuo L, Lyu MR, Shijie C (2005) Recognition of merged characters based on forepart prediction, necessity-sufficiency matching, and character-adaptive masking. IEEE Trans Syst Man Cybern B 35(1): 2–11

    Article  Google Scholar 

  • Kahan S, Pavlidis T, Baird HS (1987) On the recognition of printed characters of any font and size. IEEE Trans Pattern Anal Mach Intell 9(2): 274–288

    Article  Google Scholar 

  • Kim KK, Kim JH, Suen CY (2002) Segmentation-based recognition of handwritten touching pairs of digits using structural features. Pattern Recognit Lett 23(1–3): 13–24

    MATH  Google Scholar 

  • Kimura F, Shridhar M, Chen Z (1993) Improvements of a lexicon directed algorithm for recognition of unconstrained handwritten words. In: Proceedings of the second international conference on document analysis and recognition. pp 18–22

  • Kurniawan F, Rehman A, Dzulkifli M, Mariyam S (2009) Self organizing features map with improved segmentation to identify touching of adjacent characters in handwritten words (2011). In: Ninth international conference on hybrid intelligent systems (HIS 2009), vol 1. Shenyang, LiaoNing, China, pp 475–480

  • Kurniawan F, Rehman A, Dzulkifli M, Mariyam S, Sulong G (2011) Region-based touched character segmentation in handwritten words. Int J Innov Comput Inf Control (IJICIC) 7(6): 3107–3120

    Google Scholar 

  • Lee H-J, Lee M-C (1993) Understanding mathematical expressions in a printed document. In: Proceedings of second international conference on document analysis and recognition. pp 502–505

  • Liang S, Shridhar M, Ahmadi M (1994) Segmentation of touching characters in printed document recognition. Pattern Recognit 27(6): 825–840

    Article  Google Scholar 

  • Lorenz O, Monagan G (1994) Retrieval of line drawings. In: Proceedings of the third annual symposium on document analysis and information retrieval. Las Vegas, Nevada

  • Lorigo L, Govindaraju V (2005) Segmentation and pre-recognition of arabic handwriting. In: Proceedings of international conference on document analysis and recognition, vol 2. pp 605–609

  • Lu Y (1995) Machine printed character segmentation: an overview. Pattern Recognit 28(1): 67–80

    Article  Google Scholar 

  • Masayuki O, Syougo S, Tadashi S (1999) Segmentation of touching characters in formulas. In: Proceedings of third IAPR workshop on document analysis systems theory and practice

  • Min-Chul J, Yong-Chul S, Srihari SN (1999) Machine printed character segmentation method using side profiles. In: Proceedings of IEEE SMC ’99 conference on systems, man, and cybernetics

  • Misako S, Satoshi N (2004) Segmentation of handwritten numerals by graph representation. In: Proceedings of the ninth international workshop on frontiers in handwriting recognition

  • Monagan G (1994) A procedure for segmenting touching numbers in cadastral maps. In: Proceedings of IAPR workshop on machine vision applications (MVA 1994). Kawasaki, Japan

  • Okamoto M, Sakaguchi S, Suzuki T (1999) Segmentation of touching characters in formulas. Lect Note Comput Sci 1655:151–156

    Article  Google Scholar 

  • Oliveira LES, Lethelier E, Bortolozzi F, Sabourin R (2000) A new segmentation approach for handwritten digits. In: Proceedings of the 15th international conference on pattern recognition, vol 2. pp 323–326

  • Ouchtati S, Bedda M, Lachouri A (2007) Segmentation and recognition of handwritten numeric chains. J Comput Sci 3(4): 242–248

    Article  Google Scholar 

  • Pal U, Belaid A, Choisy C (2001) Water reservoir based approach for touching numeral segmentation. In: Proceedings sixth international conference on document analysis and recognition. pp 892–896

  • Pal U, Belaid A, Choisy C (2003) Touching numeral segmentation using water reservoir concept. Pattern Recognit Lett 24(1–3): 261–272

    Article  Google Scholar 

  • Rao AVS, Subbarao M, Rao NV, Sastry ASCS, Reddy LP (2009) Segmentation of touching handwritten numerals and alphabets. In: Second international conference on computer and electrical engineering. pp 304–307

  • Rehman A, Saba T (2011) Performance analysis of segmentation approach for cursive handwritten word recognition on benchmark database. Digit Signal Process (Elsevier) 21: 486–490

    Article  Google Scholar 

  • Roy PP, Pal U, Llados J (2008) Recognition of multi-oriented touching characters in graphical documents. In: Proceedings of sixth Indian conference on computer vision, graphics & image processing. pp 297–304

  • Rui MA, Yingnan Z, Yongquan X, Yunyang Y (2008) A touching pattern-oriented strategy for handwritten digits segmentation. In: Proceeding of international conference on computational intelligence and security. pp 174–179

  • Saba T, Rehman A (2011) Off-line cursive script recognition: current advances, comparisons and remaining problems. Artif Intell Rev. doi:10.1007/s10462-011-9229-7

  • Saba T, Rehman A, Sulong G (2010a) Improved off-line connected script recognition based on hybrid strategy. Int J Eng Sci Technol 2(6): 1603–1611

    Google Scholar 

  • Saba T, Rehman A, Sulong G (2010b) Non-linear segmentation of touched roman characters based on genetic algorithm. Int J Comput Sci Eng 2(6): 2167–2172

    Google Scholar 

  • Saba T, Rehman A, Sulong G (2010c) Touched cursive script segmentation with neural confidence. Int J Innov Comput Inf Control 7(7): 1–10

    Google Scholar 

  • Saba T, Sulong G, Rahim S, Rehman A (2010d) On the segmentation of multiple touched characters: a heuristics approach. Inf Commun Technol Lect Note Comput Sci (LNCS) Springer Verlag 101(3): 540–542. doi:10.1007/978-3-642-15766-0_91

    Google Scholar 

  • Saba T, Sulong G, Rehman A (2011) Document image analysis: issues, comparison of methods and remaining problems. Artif Intell Rev 35(2): 101–118. doi:10.1007/s10462-010-9186-6

    Article  Google Scholar 

  • Seo W, Cho BJ (2004) Efficient segmentation path generation for unconstrained handwritten Hangul characters. Lect Note Artif Intell 3192: 438–446

    Google Scholar 

  • Shi Z, Govindaraju V (1997) Segmentation and recognition of connected handwritten numeral strings. Pattern Recognit 30(9): 1501–1504

    Article  Google Scholar 

  • Strathy NW, Suen CY, Krzyzak A (1993) Segmentation of handwritten digits using contour features. In: Proceedings of the second international conference on document analysis and recognition. pp 577–580

  • Suwa M (2005) Segmentation of connected handwritten numerals by graph representation. In: Proceedings of eighth international conference on document analysis and recognition, vol 2. pp 750–754

  • Teruyuki Y, Shinji T, Tomohiro Y, Tsuyoshi S, Eiji M, Hisao O (2002) A segmentation system for touching handwritten Japanese characters. In: Proceedings of the eighth international workshop on frontiers in handwriting recognition (IWFHR’02). pp 407–412

  • Tian X, Zhang Y (2007) Segmentation of touching characters in mathematical expressions using contour feature technique. In: Eighth ACIS international conference on software engineering, artificial intelligence, networking, and parallel/distributed computing. pp 206–209

  • Tripathy N, Pal U (2004) Handwriting segmentation of un-constrained Oriya text. In: Proceedings of the international workshop on frontiers in handwriting recognition. pp 306–311

  • Tsujimoto S, Assada H (1991) Resolving ambiguity in segmenting touching characters. In: Proceedings of the first international conference on document analysis and recognition

  • Ventzislav A (2004) Using critical points in contours for segmentation of touching characters. In: Proceedings of the 5th international conference on computer systems and technologies

  • Wei X, Ma S (2005) Segmentation of touching Chinese character based on convex hull ratio feature. J Chin Inf Process 47: 91–96

    Google Scholar 

  • Wei X, Ma S, Jin Y (2005) Segmentation of connected Chinese characters based on genetic algorithm. In: Proceedings of the eighth international conference on document analysis and recognition (ICDAR’05), vol 2. pp 645–649

  • Wshah S, Shi Z, Govindaraju V (2009a) Segmentation of Arabic handwriting based on both contour and skeleton segmentation. In: Proceedings of the tenth international conference on document analysis and recognition. pp 793–797

  • Wshah S, Shi Z, Govindaraju V (2009b) Segmentation of Arabic handwriting based on both contour and skeleton segmentation In: Proceedings of the 10th international conference on document analysis and recognition. pp 793–797

  • Xian W, Govindaraju V, Srihari S (1999) Multi-experts for touching digit string recognition. In: Proceedings of the fifth international conference on document analysis and recognition. pp 800–803

  • Xianghui W, Shaoping M, Yijiang J (2005) Segmentation of connected Chinese characters based on genetic algorithm. Paper presented at the proceedings of the eighth international conference on document analysis and recognition

  • Yamaguchi T, Yoshikawa T, Shinogi T, Tsuruoka S, Teramoto M (2001) A segmentation method for touching Japanese handwritten characters based on connecting condition of lines. In: Proceedings of sixth international conference on document analysis and recognition. pp 837–841

  • Yi-Kai C, Jhing-Fa W (2000) Segmentation of single or multiple-touching handwritten numeral string using background and foreground analysis. IEEE Trans Pattern Anal Mach Intell 22(11): 1304–1317

    Article  Google Scholar 

  • Yong G, Yan Z, Zhao H (2009a) Touching string segmentation using MRF. In: International conference on computational intelligence and security. pp 520–524

  • Yong G, Yan Z, Zhao H (2009b) Touching string segmentation using MRF. In: International conference on computational intelligence and security. pp 520–524

  • Yong G, Yan Z, Zhao H (2009c) Touching string segmentation using MRF. In: International conference on computational intelligence and security. pp 520–524

  • Yoon JJ, Kim G (2000) An approach for active segmentation of unconstrained handwritten Korean strings using run-length code. In: Proceedings of the seventh international workshop on frontiers in handwriting recognition. Amsterdam

  • Yu D, Yan H (2001) Separation of touching handwritten multi-numeral strings based on morphological structural features. Pattern Recognit 34(3): 587–599

    Article  MATH  Google Scholar 

  • Yun L, Liu CS, Ding XQ, Qiang F (2004) A recognition based system for segmentation of touching handwritten numeral strings. In: Proceedings of the ninth international workshop on frontiers in handwriting recognition. pp 294–299

  • Zhang JY, Ding XQ (2000) Multi-scale feature extraction and nested-subset classifier design for high accuracy handwritten character recognition. Paper presented at the, Barcelona, Spain

  • Zhang S, Karim MA (2002) A new impulse detector for switching median filters. IEEE Signal Process Lett 9: 360–363

    Article  Google Scholar 

  • Zhang LQ, Suen CY (2002) Recognition of courtesy amounts on bank checks based on a segmentation approach. In: Proceedings of eighth international workshop on handwriting recognition. pp 298–302

  • Zhang T, Wang X, Chen C, Liu J (2009) Connected numeral strings segmentation based on the combination of characteristic position and contour detecting. In: Proceedings of the first international conference on digital image processing. pp 81–84

  • Zhongkang L, Zheru C, Wan-Chi S, Pengfei S (1999) A background-thinnig-based approach for separating and recognizing connected handwritten digit strings. Pattern Recognit 32: 921–933

    Article  Google Scholar 

  • Zhu X, Yin X (2002) A new textual/non-textual classifier for document skew correction. In: Proceedings of the 16th international conference on pattern recognition (ICPR). pp 480–482

Download references

Author information

Authors and Affiliations

  1. Graphics and Multimedia Department Faculty of Computer Science & Information Systems, Universiti Teknologi Malaysia, Johor Bahru, Malaysia

    Tanzila Saba

  2. A.I. and Robotics Research Group, College of Computer and Information Sciences, Al-Imam M. Saud Islamic University, Riyadh, Kingdom of Saudi Arabia

    Amjad Rehman & Mohamed Elarbi-Boudihir

Authors
  1. Tanzila Saba
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Amjad Rehman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohamed Elarbi-Boudihir
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Amjad Rehman.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Saba, T., Rehman, A. & Elarbi-Boudihir, M. Methods and strategies on off-line cursive touched characters segmentation: a directional review. Artif Intell Rev 42, 1047–1066 (2014). https://doi.org/10.1007/s10462-011-9271-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-011-9271-5

Keywords

Search

Navigation