Skip to main content
SpringerLink
Log in

Offline Odia handwritten character recognition with a focus on compound characters

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Recognition of Odia character images is one of the ongoing applications of offline OCR. An attempt has been made here to develop an efficient feature extraction procedure that can assist the recognition of Odia handwritten digits, basic characters, and compound characters. Three different kinds of strategies have been carried here for character recognition. First, the various characters are recognized using three feature extraction procedures individually, followed by a merged feature set with a set of standard machine learning algorithms. In the second approach, the recognition of the characters is performed by popular RNN and CNN by providing the same feature set instead of giving immediate images, unlike traditional networks. The same feature sets, as well as classifiers, are applied to recognize different categories of characters. The third task was to incorporate a set of Odia compound characters into our suggested character recognition framework. The dataset that has been created for this purpose consists of numerals, basic characters, and compound characters. The proposed method achieves a recognition accuracy of 86.56% on this dataset with 112 classes of characters.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. https://www.isical.ac.in/~ujjwal/download/OriyaNumeral.html

  2. https://www.iitbbs.ac.in/profile.php/nbpuhan/

  3. https://nitrkl.ac.in/CS/Datasets.aspx

  4. https://www.iiit-bh.ac.in/academics/research/funded-projects/clia

References

  1. Agrawal P, Chaudhary D, Madaan V, Zabrovskiy A, Prodan R, Kimovski D, Timmerer C (2021) Automated bank cheque verification using image processing and deep learning methods. Multimed Tools Appl 80(4):5319–5350

    Article  Google Scholar 

  2. Baruch O (1988) Line thinning by line following. Pattern Recogn Lett 8(4):271–276

    Article  Google Scholar 

  3. Bhattacharya U, Chaudhuri B (2005) Databases for research on recognition of handwritten characters of indian scripts. In: Eighth international conference on document analysis and recognition (ICDAR’05). IEEE, pp 789–793

  4. Bhowmik TK, Parui SK, Bhattacharya U, Shaw B (2006) An hmm based recognition scheme for handwritten oriya numerals. In: 9th international conference on information technology (ICIT’06). IEEE, pp 105–110

  5. Das D, Dash R, Majhi B (2018) Optimization based feature generation for handwritten odia-numeral recognition. In: 2018 fourteenth international conference on information processing (ICINPRO). IEEE, pp 1–5

  6. Das D, Nayak DR, Dash R, Majhi B (2019) An empirical evaluation of extreme learning machine: application to handwritten character recognition. Multimed Tools Appl 78(14):19495–19523

    Article  Google Scholar 

  7. Das D, Nayak DR, Dash R, Majhi B (2020) Mjcn: Multi-objective jaya convolutional network for handwritten optical character recognition. Multimed Tools Appl 79(43):33023–33042

    Article  Google Scholar 

  8. Das N, Acharya K, Sarkar R, Basu S, Kundu M, Nasipuri M (2014) A benchmark image database of isolated bangla handwritten compound characters. Int J Doc Anal Recog (IJDAR) 17(4):413–431

    Article  Google Scholar 

  9. Dash KS, Puhan N, Panda G (2014) A hybrid feature and discriminant classifier for high accuracy handwritten odia numeral recognition. In: 2014 IEEE region 10 symposium. IEEE, pp 531–535

  10. Dash KS, Puhan NB, Panda G (2015) Handwritten numeral recognition using non-redundant stockwell transform and bio-inspired optimal zoning. IET Image Process 9(10):874–882

    Article  Google Scholar 

  11. Dash KS, Puhan NB, Panda G (2015) On extraction of features for handwritten odia numeral recognition in transformed domain. In: 2015 eighth international conference on advances in pattern recognition (ICAPR). IEEE, pp 1–6

  12. Dash KS, Puhan NB, Panda G (2017) Odia character recognition: a directional review. Artif Intell Rev 48(4):473–497

    Article  Google Scholar 

  13. Dash KS, Puhan NB, Panda G (2020) Sparse concept coded tetrolet transform for unconstrained odia character recognition. arXiv:2004.01551

  14. Dey R, Balabantaray RC (2019) A novel sliding window approach for offline handwritten character recognition. In: 2019 international conference on information technology (ICIT). IEEE, pp 178–183

  15. Dey R, Balabantaray RC, Mohanty S (2021) Sliding window based off-line handwritten text recognition using edit distance. Multimed Tools Appl. https://doi.org/10.1007/s11042-021-10988-9

  16. Dey R, Balabantaray RC, Piri J (2020) A robust handwritten digit recognition system based on sliding window with edit distance. In: 2020 IEEE international conference on electronics, computing and communication technologies (CONECCT). IEEE, pp 1–6

  17. Guo Y, Liu Y, Bakker EM, Guo Y, Lew MS (2018) Cnn-rnn: a large-scale hierarchical image classification framework. Multimed Tools Appl 77(8):10251–10271

    Article  Google Scholar 

  18. Huh JH (2020) Surgery agreement signature authentication system for mobile health care. Electronics 9(6):890

    Article  Google Scholar 

  19. Huh JH, Seo YS (2019) Understanding edge computing: Engineering evolution with artificial intelligence. IEEE Access 7:164229–164245

    Article  Google Scholar 

  20. Jindal T, Bhattacharya U (2013) Recognition of offline handwritten numerals using an ensemble of mlps combined by adaboost. In: Proceedings of the 4th international workshop on multilingual OCR, pp 1–5

  21. Justusson B (1981) Median filtering: Statistical properties. In: Two-dimensional digital signal prcessing II. Springer, pp 161–196

  22. Kaur RP, Kumar M, Jindal MK (2019) Newspaper text recognition of gurumukhi script using random forest classifier. Multimed Tools Appl:1–14

  23. Lempitsky V, Kohli P, Rother C, Sharp T (2009) Image segmentation with a bounding box prior. In: 2009 IEEE 12th international conference on computer vision. IEEE, pp 277–284

  24. Maalej R, Kherallah M (2020) Improving the dblstm for on-line arabic handwriting recognition. Multimed Tools Appl 79(25):17969–17990

    Article  Google Scholar 

  25. Majhi B, Pujari P (2018) On development and performance evaluation of novel odia handwritten digit recognition methods. Arab J Sci Eng 43 (8):3887–3901

    Article  Google Scholar 

  26. Maswadi K, Ghani NA, Hamid S, Rasheed MB (2021) Human activity classification using decision tree and naïve bayes classifiers. Multimed Tools Appl:1–18

  27. Mohapatra RK, Mishra TK, Panda S, Majhi B (2015) Ohcs: A database for handwritten atomic odia character recognition. In: 2015 fifth national conference on computer vision, pattern recognition, image processing and graphics (NCVPRIPG). IEEE, pp 1–4

  28. Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66

    Article  Google Scholar 

  29. Pal U, Sharma N, Wakabayashi T, Kimura F (2007) Handwritten numeral recognition of six popular indian scripts. In: Ninth international conference on document analysis and recognition (ICDAR 2007), vol 2. IEEE, pp 749–753

  30. Pramanik R, Bag S (2018) Shape decomposition-based handwritten compound character recognition for bangla ocr. J Vis Commun Image Represent 50:123–134

    Article  Google Scholar 

  31. Rehman A, Naz S, Razzak MI (2019) Writer identification using machine learning approaches: a comprehensive review. Multimed Tools Appl 78 (8):10889–10931

    Article  Google Scholar 

  32. Roy K, Pal T, Pal U, Kimura F (2005) Oriya handwritten numeral recognition system. In: Eighth international conference on document analysis and recognition (ICDAR’05). IEEE, pp 770–774

  33. Roy S, Das N, Kundu M, Nasipuri M (2017) Handwritten isolated bangla compound character recognition: a new benchmark using a novel deep learning approach. Pattern Recogn Lett 90:15–21

    Article  Google Scholar 

  34. Sarangi PK, Ahmed P, Ravulakollu KK (2014) Naïve bayes classifier with lu factorization for recognition of handwritten odia numerals. Indian Jo Sci Technol 7(1):35–38

    Article  Google Scholar 

  35. Sebti A, Hassanpour H (2017) Body orientation estimation with the ensemble of logistic regression classifiers. Multimed Tools Appl 76(22):23589–23605

    Article  Google Scholar 

  36. Sethy A, Patra PK (2016) Off-line odia handwritten numeral recognition using neural network: a comparative analysis. In: 2016 international conference on computing, communication and automation (ICCCA). IEEE, pp 1099–1103

  37. Sethy A, Patra PK (2019) Off-line odia handwritten character recognition: an axis constellation model based research. Int J Innov Technol Exploring Eng (IJITEE) 8(9S2):788–793

    Article  Google Scholar 

  38. Sethy A, Patra PK, Nayak DR (2018) Off-line handwritten odia character recognition using dwt and pca. In: Progress in advanced computing and intelligent engineering. Springer, pp 187–195

  39. Sethy A, Patra PK, Nayak S, Jena PM (2017) Symmetric axis based off-line odia handwritten character and numeral recognition. In: 2017 3rd international conference on computational intelligence and networks (CINE). IEEE, pp 83–87

  40. Sethy A, Patra PK, Nayak SR (2020) Offline handwritten numeral recognition using convolution neural network. Mach Vis Inspection Syst Image Process Concepts Methodologies Appl 1:197–212

    Google Scholar 

  41. Singh PK, Sarkar R, Das N, Basu S, Kundu M, Nasipuri M (2018) Benchmark databases of handwritten bangla-roman and devanagari-roman mixed-script document images. Multimed Tools Appl 77(7):8441–8473

    Article  Google Scholar 

  42. Tripathy N, Panda M, Pal U (2003) System for oriya handwritten numeral recognition. In: Document recognition and retrieval XI. International Society for Optics and Photonics, vol 5296, pp 174–181

Download references

Author information

Authors and Affiliations

  1. International Institute of Information Technology, Bhubaneswar, India

    Raghunath Dey & Rakesh Chandra Balabantaray

  2. Sri Sri University, Cuttack, India

    Sanghamitra Mohanty

Authors
  1. Raghunath Dey
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rakesh Chandra Balabantaray
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sanghamitra Mohanty
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Raghunath Dey.

Ethics declarations

Conflict of Interests

The authors declare that there are no conflicts of interest.

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dey, R., Balabantaray, R.C. & Mohanty, S. Offline Odia handwritten character recognition with a focus on compound characters. Multimed Tools Appl 81, 10469–10495 (2022). https://doi.org/10.1007/s11042-022-12148-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12148-z

Keywords

Search

Navigation