Segmentation of handwritten words using structured support vector machine

Abstract

Words and characters segmentation is a most indispensable and fundamental task for the handwritten script recognition. However, the complex language structures, deviation in pen breadth and slant in inscription make the feature extraction process very challenging. In this research, a binary quadratic process has been formulated for the word segmentation. It deliberates a co-relationship between the inter-word gap and intra-word gap. The structured support vector machine is used for the experiment. Experimental results of public datasets (i.e., ICDAR2009 and ICDAR2013) show state-of-the-art performance of the designed algorithm.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

References

  1. 1.

    Dhaka VP, Sharma MK (2015) An efficient segmentation technique for Devanagari offline handwritten scripts using feedforward neural network. Neural Comput Appl 26(8):1881–1893

    Google Scholar 

  2. 2.

    Ryu J, Koo HI, Cho NI (2015) Word segmentation method for handwritten documents based on structured learning. IEEE Signal Process Lett 22(8):1161–1165

    Google Scholar 

  3. 3.

    Sharma MK, Dhaka VP (2016) Segmentation of English offline handwritten cursive scripts using a feedforward neural network. Neural Comput Appl 27(5):1369–1379

    Google Scholar 

  4. 4.

    Sharma MK, Dhaka VP (2016) Pixel plot and trace based segmentation method for bilingual handwritten scripts using feedforward neural network. Neural Comput Appl 27(7):1817–1829

    Google Scholar 

  5. 5.

    Sharma MK, Dhaka VP (2015) Offline scripting-free author identification based on speeded-up robust features. Int J Doc Anal Recognit (IJDAR) 18(4):303–316

    Google Scholar 

  6. 6.

    Sharma MK, Dhaka VP (2015) Offline language-free writer identification based on speeded-up robust features. Int J Eng (IJE) IJE Trans A: Basics 28(7):984–994

    Google Scholar 

  7. 7.

    Gatos B, Stamatopoulos N, Louloudis G (2009) ICDAR2009 handwriting segmentation contest. In: Proceedings of international conference on document analysis and recognition (ICDAR), pp 1393–1397

  8. 8.

    Gatos B, Stamatopoulos N, Louloudis G (2011) ICDAR2009 handwriting segmentation contest. Int J Doc Anal Recognit (IJDAR) 14(1):25–33

    Google Scholar 

  9. 9.

    Stamatopoulos N, Gatos B, Louloudis G, Pal U and Alaei A (2013) ICDAR 2013 handwriting segmentation contest. In: 12th international conference on document analysis and recognition (ICDAR), pp 1402–1406

  10. 10.

    Jindal P, Jindal B (2015) Line and word segmentation of handwritten text documents written in gurumukhi script using mid point detection technique. In: Proceedings of 2015 RAECS UIET Panjab University Chandigarh. https://doi.org/10.1109/raecs.2015.7453388. Accessed 21–22 Dec 2015

  11. 11.

    Mehdi M, Riaz A (2013) Optimized word segmentation for the word based cursive handwriting recognition. In: 2013 European modelling symposium, 20–22 Nov 2013, pp 299–304. https://doi.org/10.1109/EMS.2013.52

  12. 12.

    Jain S, Singh H (2014) A novel approach for word segmentation in correlation based OCR system. Int J Comput Appl 99(18):12–20

    Google Scholar 

  13. 13.

    Karmakar P, Nayak B, Bhoi N (2014) Line and Word segmentation of a printed text document. Int J Comput Sci Inf Technol 5(1):157–160

    Google Scholar 

  14. 14.

    Jindal S, Lehal G (2012) Line segmentation of handwritten Gurmukhi manuscripts. In: Proceedings of the 3rd international on advance computing conference, Institute of Electrical and Electronics Engineers, Mumbai, pp 1797–1801

  15. 15.

    Dahake D, Sharma RK, Singh H (2017) On segmentation of words from online handwritten Gurmukhi sentences. In: 2017 2nd international conference on man and machine interfacing (MAMI). https://doi.org/10.1109/mami.2017.8307870. Accessed 21–23 Dec 2017

  16. 16.

    Ladwani VM, Malik L (2011) Novel approach to segmentation of handwritten Devnagari word. In: Third international conference on emerging trends in engineering and technology, pp 219–224. https://doi.org/10.1109/icetet.2010.143. Accessed 31 Jan 2011

  17. 17.

    Shaw B, Parui SK, Shridhar M (2008) Offline handwritten Devnagari word recognition: a segmentation based approach. In: 19th international conference on pattern recognition, pp 1–4

  18. 18.

    Chaudhuri BB, Pal U (1997) An OCR system to read two Indian language scripts: Bangla and Devnagari (Hindi). In: Proceedings of the fourth international conference on document analysis and recognition, pp 1011–1015. 18–20 Aug 1997

  19. 19.

    Mahadevan U, Nagabushnam R (1995) Gap metrics for word separation in handwritten lines. In: Proceedings of international conference on document analysis and recognition (ICDAR), pp 124–127

  20. 20.

    Seni G, Cohen E (1994) External word segmentation of off-line handwritten text lines. Pattern Recogn 27(1):41–52

    Google Scholar 

  21. 21.

    Papavassiliou V, Stafylakis T, Katsouros V, Carayannis G (2010) Handwritten document image segmentation into text lines and words. Pattern Recogn 43(1):369–377

    MATH  Google Scholar 

  22. 22.

    Stafylakis T, Papavassiliou V, Katsouros V, Carayannis G (2008) Robust text-line and word segmentation for handwritten documents. In: Images, proceedings of IEEE international conference acoustics, speech and signal processing (ICASSP), pp 3393–3396

  23. 23.

    Kim HS, Jeong S, Lee SG, Suen YC (2001) Word segmentation in handwritten Korean text lines based on gap clustering techniques. In: Proceedings of international conference on document analysis and recognition (ICDAR), pp 189–193

  24. 24.

    Louloudis G, Gatos B, Pratikakis I, Halatsis C (2009) Text line and word segmentation of handwritten documents. Pattern Recogn 42(12):3169–3183

    MATH  Google Scholar 

  25. 25.

    Manmatha R, Rothfeder LJ (2005) A scale space approach for automatically segmenting words from historical handwritten documents. IEEE Trans Pattern Anal Mach Intell 27(8):1212–1225

    Google Scholar 

  26. 26.

    Kim G, Govindaraju V, Srihari S (1996) A segmentation and recognition strategy for handwritten phrases. In: Proceedings of international conference on pattern recognition, pp 510–514

  27. 27.

    Srihari S, Srinivasan H, Babu P, Bhole C (2005) Handwritten Arabic word spotting using the cedarabic document analysis system. In: Proceedings of symposium document image understanding technology, pp 123–132

  28. 28.

    Yin F, Liu CL (2009) Handwritten Chinese text line segmentation by clustering with distance metric learning. Pattern Recogn 42(12):3146–3157

    MATH  Google Scholar 

  29. 29.

    Koo IH, Cho IN (2012) Text-line extraction in handwritten Chinese documents based on an energy minimization framework. IEEE Trans Image Process 21(3):1169–1175

    MathSciNet  MATH  Google Scholar 

  30. 30.

    Ling H, Jing W, Ruolan Z (2010) The classification research of support vector machine based on spot for hyperspectral remote sensing application. In: International conference on computational and information sciences (ICCIS), pp 1009–1012. https://doi.org/10.1109/iccis.2010.249. Accessed on 17–19, 2010

  31. 31.

    Kilic N, Gorgel P, Ucan ON, Kala A (2008) Multifont Ottoman character recognition using support vector machine. In: 3rd international symposium on communications, control and signal processing (ISCCSP 2008), pp 328–333. https://doi.org/10.1109/isccsp.2008.4537244. Accessed on 12–14, 2008

  32. 32.

    Nguyen T-N, Vo D-H, Huynh H-H, Meunier J (2014) Geometry-based static hand gesture recognition using support vector machine. In: 13th international conference on control automation robotics and vision (ICARCV 2014), pp 769–774. https://doi.org/10.1109/icarcv.2014.7064401. Accessed 10–12, 2014

  33. 33.

    Bai X, Huigang Z, Jun Z (2014) VHR object detection based on structural feature extraction and query expansion. IEEE Trans Geosci Remote Sens 52(10):6508–6520

    Google Scholar 

  34. 34.

    Hui X, Songcan C, Qiang Y (2011) Structural regularized support vector machine: a framework for structural large margin classifier. IEEE Trans Neural Netw 22(4):573–587

    Google Scholar 

  35. 35.

    Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Int. J. Comput Vis Image Underst 110:246–359

    Google Scholar 

  36. 36.

    Meyer TR, Zefran M, Decarlo AR (2014) A comparison of the embedding method with multi-parametric programming, mixed-integer programming, gradient-descent, and hybrid minimum principle-based methods. IEEE Trans Control Syst Technol 22(5):1784–1800

    Google Scholar 

  37. 37.

    Wang QM, Gooi BH, Chen XS, Lu S (2014) A mixed integer quadratic programming for dynamic economic dispatch with value point effect. IEEE Trans Power Syst 29(5):2097–2106

    Google Scholar 

  38. 38.

    Tsochantaridis I, Joachims T, Hofmann T, Altun Y (2005) Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6:1453–1484

    MathSciNet  MATH  Google Scholar 

  39. 39.

    Tsochantaridis I, Joachims T, Hofmann T, Altun Y (2004) Support vector machine learning for inter dependent and structured output spaces. In: Proceedings of international conference on machine learning, pp 104–111

  40. 40.

    Caetano T, McAuley J, Cheng L, Le VQ, Smola A (2009) Learning graph matching. IEEE Trans Pattern Anal Mach Intell 31(6):1048–1058

    Google Scholar 

  41. 41.

    Li P, Guo S, Cheng Z (2013) Max–min lifetime optimization for cooperative communications in multi-channel wireless networks. IEEE Trans Parallel Distrib Syst 25(6):1533–1542

    Google Scholar 

  42. 42.

    Joachims T, Finley T, Yu NJC (2009) Cutting-plane training of structural SVMs. Mach Learn 77(1):27–59

    MATH  Google Scholar 

  43. 43.

    Shui P-L, Zhang W-C (2013) Corner detection and classification using anisotropic directional derivative representations. IEEE Trans Image Process 22:3204–3218

    Google Scholar 

  44. 44.

    Awrangjeb M, Lu G, Fraser CS (2012) Performance comparisons of contour-based corner detectors. IEEE Trans Image Process 21:4167–4179

    MathSciNet  MATH  Google Scholar 

  45. 45.

    Escalera AD, Armingol JM (2010) Automatic chessboard detection for intrinsic and extrinsic camera parameter calibration. Sensors 10:2027–2044

    Google Scholar 

  46. 46.

    Forlenza L, Carton P, Accardo D, Fasano G, Moccia A (2012) Real time corner detection for miniaturized electro-optical sensors onboard small unmanned aerial systems. Sensors 12:863–877

    Google Scholar 

  47. 47.

    Awrangjeb M (2008) Contour-based corner detection and robust geometric point matching techniques. Ph.D. Thesis, Monash University, Melbourne, Australia

  48. 48.

    Zitova B, Flusser J (2003) Image registration methods: a survey. Image Vis Comput 21:977–1000

    Google Scholar 

  49. 49.

    Kahaki SMM, Nordin MJ, Ashtari AH (2014) Contour-based corner detection and classification by using mean projection transform. Sensors 14:4126–4143

    Google Scholar 

  50. 50.

    IBM ILOGCPLEX Optimizer. http://www-01.ibm.com/software/integration/optimization/cplex-optimizer/. Accessed 2 June 2018

  51. 51.

    Kim S, Nowozin S, Kohli P, Yoo C (2013) Task-specific image partitioning. IEEE Trans Image Process 22(2):488–500

    MathSciNet  MATH  Google Scholar 

  52. 52.

    Chang CJ (2006) Distance-increasing mappings from binary vectors to permutations that increase hamming distances by at least two. IEEE Trans Inf Theory 52(4):1683–1689

    MathSciNet  MATH  Google Scholar 

  53. 53.

    Phillips I, Chhabra A (1999) Empirical performance evaluation of graphics recognition systems. IEEE Trans Pattern Anal Mach Intell 21(9):849–870

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Vijaypal Singh Dhaka.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sharma, M.K., Dhaka, V.S. Segmentation of handwritten words using structured support vector machine. Pattern Anal Applic 23, 1355–1367 (2020). https://doi.org/10.1007/s10044-019-00843-x

Download citation

Keywords

  • S-SVM
  • Inter-word
  • Intra-word
  • SURF descriptors, SO