Skip to main content
SpringerLink
Log in

Improved recognition results of offline handwritten Gurumukhi characters using hybrid features and adaptive boosting

  • Data analytics and machine learning
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Offline handwritten character recognition is a part of the arduous area of research in the domain of document analysis and recognition. In order to enhance the recognition results of offline handwritten Gurumukhi characters, the authors have applied hybrid features and adaptive boosting approach in this paper. On feature extraction stage, zoning, diagonal, centroid, and peak extent-based features have been taken into account for extracting the meaningful information about each character. On the classification stage, three classifiers, namely decision tree, random forest, and convolution neural network classifier, are used. For experimental work, the authors have collected 14,000 pre-segmented samples of Gurumukhi characters (35-class problem) written by 400 writers where they have used 70% data as training set and remaining 30% data as testing set. The authors have also explored fivefold cross-validation technique for experimental work. The AdaBoost approach along with the fivefold cross-validation strategy outstands the existing techniques in the relevant field with the recognition accuracy of 96.3%.

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

Similar content being viewed by others

References

  • Ahranjany SS, Razzazi F, Ghassemian MH (2010) A very high accuracy handwritten character recognition system for Farsi/Arabic digits using convolutional neural networks. In: Proceedings of the IEEE 5th international conference on bio-inspired computing: theories and applications (BIC-TA), pp. 1585–1592

  • Alaei A, Nagabhushan P, Pal U (2010) A new two-stage scheme for the recognition of Persian handwritten characters. In: Proceedings of the 12th international conference on frontiers in handwriting recognition (ICFHR), pp. 130–135

  • Antony PJ, Savitha CK and Ujwal UJ (2016) Haar features based handwritten character recognition system for tulu script. In: Proceedings of the IEEE International conference on recent trends in electronics information communication technology, pp. 65–68

  • Ardeshana M, Sharma AK, Adhyaru DM, Zaveri TH (2016) Handwritten Gujarati character recognition based on discrete cosine transform. In: Proceedings of the IRF-IEEE forum international conference, pp. 23–26

  • Bhadouria VS, Ghoshal D, Siddiqi AH (2014) A new approach for high density saturated impulse noise removal using decision-based coupled window median filter. SIViP 8:71–84

    Article  Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  Google Scholar 

  • Dargan S, Kumar M (2018) Writer identification system for indic and non-indic scripts: state-of-the-art survey. Arch Comput Methods Eng. https://doi.org/10.1007/s11831-018-9278-z

    Article  Google Scholar 

  • Elbashir MK, Mustafa ME (2018) Convolutional neural network model for arabic handwritten characters recognition. Int J Adv Res Comput Commun Eng 7(11):1–5

    Article  Google Scholar 

  • Freund Y, Schapire RE (1999) A short introduction to boosting. J Jpn Soc Artif Intell 14(5):771–780

    Google Scholar 

  • Garg N (2009) Handwritten Gurumukhi Character recognition using neural networks, M.E. thesis, Thapar University, Patiala, India

  • Gohell CC, Goswam MM, Prajapate YK (2015) On-line handwritten Gujarati character recognition using low level stroke. In: Proceedings of the third international conference on image information processing, pp. 130–134

  • Gupta S, Kumar M (2019) Forensic document examination system using boosting and bagging methodologies. Soft Comput. https://doi.org/10.1007/s00500-019-04297-5

    Article  Google Scholar 

  • Husnain M, Missen MMS, Mumtaz S, Jhandir MZ, Coustaty M, Luqman MM, Ogier JM, Choi GS (2019) Recognition of Urdu handwritten characters using convolutional neural network. Appl Sci. https://doi.org/10.3390/app9132758

    Article  Google Scholar 

  • Joseph JS, LakshmiKiranParthiban CUP (2019) An efficient offline handwritten character recognition using CNN and Xgboost. Int J Innov Technol Explor Eng 8(6):115–118

    Google Scholar 

  • Kaur H, Kumar M (2021) On the recognition of offline handwritten word using holistic approach and AdaBoost methodology. Multimed Tools Appl 80:11155–11175

    Article  Google Scholar 

  • Kavitha BR, Srimathi C (2019) Benchmarking on offline handwritten Tamil character recognition using convolutional neural networks. J King Saud Univ-Comput Inf Sci. https://doi.org/10.1016/j.jksuci.2019.06.004

    Article  Google Scholar 

  • Koundal K, Kumar M, Garg NK (2017) Punjabi optical character recognition: a survey. Indian J Sci Technol 10(19):1–8

    Article  Google Scholar 

  • Kumar M, Sharma RK, Jindal MK (2013a) A novel feature extraction technique for offline handwritten Gurumukhi character recognition. IETE J Res 59(6):687–692

    Article  Google Scholar 

  • Kumar M, Jindal MK, Sharma RK (2013b) MDP Feature extraction technique for offline handwritten Gurumukhi character recognition. Smart Comput Rev 3(6):397–404

    Article  Google Scholar 

  • Kumar M, Sharma RK, Jindal MK (2014) A novel hierarchical technique for offline handwritten Gurumukhi character recognition. Natl Acad Sci Lett 37(6):567–572

    Article  Google Scholar 

  • Kumar M, Jindal MK, Sharma RK (2016) Offline handwritten Gurumukhi character recognition: analytical study of different transformations. Proc Natl Acad Sci, India, Sect A 87(1):137–143

    Article  Google Scholar 

  • Kumar M, Jindal MK, Sharma RK, Jindal SR (2018a) Character and numeral recognition for non-Indic and Indic scripts: a survey. Artif Intell Rev. https://doi.org/10.1007/s10462-017-9607-x

    Article  Google Scholar 

  • Kumar M, Jindal SR, Jindal MK, Lehal GS (2018b) Improved recognition results of medieval handwritten Gurumukhi manuscripts using boosting and bagging methodologies. Neural Process Lett. https://doi.org/10.1007/s11063-018-9913-6

    Article  Google Scholar 

  • Kumar M, Jindal MK, Sharma RK, Jindal SR (2019) Performance evaluation of classifiers for the recognition of offline handwritten Gurumukhi characters and numerals: a study. Artif Intell Rev. https://doi.org/10.1007/s10462-019-09727-2

    Article  Google Scholar 

  • Kumar M, Jindal MK, Sharma RK (2011) k-Nearest neighbor based offline handwritten Gurumukhi character recognition. In: Proceedings of the international conference on image information processing, Jaypee University of Information Technology, Waknaghat (Shimla), pp. 1–4

  • Kumar M, Jindal MK, Sharma RK (2012) Offline handwritten Gurumukhi character recognition: study of different features and classifiers combinations. In: Proceedings of the workshop on document analysis and recognition, IIT Bombay, pp. 94–99

  • Kumar M (2015) Offline handwritten Gurumukhi script recognition, Ph. D. thesis, Thapar University, Patiala, India

  • LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  • Lehal GS, Singh C (1999) Feature extraction and classification for OCR of Gurumukhi script. Vivek 12(2):2–12

    Google Scholar 

  • Masita KL, Hasan AN and Shongwe T (2020) Deep learning in object detection: a review. In: Proceedings of international conference on artificial intelligence, big data, computing and data communication systems, pp. 1–11

  • Ptucha R, Such FP, Pillai S, Brockler F, Singh V, Hutowski P (2019) Intelligent character recognition using fully convolutional neural networks. Pattern Recogn 88(2019):604–613

    Article  Google Scholar 

  • Rampalli R, Ramakrishnan AG (2011) Fusion of complementary online and offline strategies for recognition of handwritten Kannada characters. J Univ Comput Sci (JUCS) 17(1):81–93

    Google Scholar 

  • Saabni R (2015) Ada-boosting extreme learning machines for handwritten digit and digit strings recognition. In: Proceedings of the 5th international conference on digital information processing and communications.

  • Schomaker L, Segers E (1999) Finding features used in the human reading of cursive handwriting. IJDAR 2:13–18

    Article  Google Scholar 

  • Schwenk H, Bengio Y (1997) AdaBoosting neural networks: application to on-line character recognition. In: Proceedings of the international conference on artificial neural network, pp. 967–972

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

    Article  Google Scholar 

  • Shahin AA (2017) Printed Arabic text recognition using linear and non-linear regression. Int J Adv Comput Syst Appl 8(1):227–235

    Google Scholar 

  • Sharma DV, Jain U (2010) Recognition of isolated handwritten characters of Gurumukhi script using neocognitron. Int J Comput Appl 10(8):10–16

    Google Scholar 

  • Siddharth KS, Jangid M, Dhir R, Rani R (2011) Handwritten Gurumukhi character recognition using statistical and background directional distribution features. Int J Comput Sci Eng 3(6):2332–2345

    Google Scholar 

  • Singh P, Budhiraja S (2012) Offline handwritten Gurumukhi numeral recognition using wavelet transforms. Int J Mod Educ Comput Sci 8:34–39

    Article  Google Scholar 

  • Venkatesh N, Ramakrishnan AG (2011) Choice of classifiers in hierarchical recognition of online handwritten Kannada and Tamil aksharas. J Univ Comput Sci (JUCS) 17:94–106

    Google Scholar 

  • Wang H, Zhu C, Shen J, Zhang Z, Shi X (2021) Salient object detection by robust foreground and background seed selection. Comput Electr Eng. https://doi.org/10.1016/j.compeleceng.2021.106993

    Article  Google Scholar 

  • Yuan J, Xiong H-C, Xiao Y, Guan W, Wang M, Hong R, Li Z-Y (2019) Gated CNN: integrating multi-scale feature layers for object detection. Pattern Recogn 105:1–28

    Google Scholar 

  • Zhang TY, Suen CY (1984) A fast parallel algorithm for thinning digital patterns. Commun ACM 27(3):236–239

    Article  Google Scholar 

  • Zhu B, Zhou XD, Liu CL, Nakagawa M (2010) A robust model for on-line handwritten Japanese text recognition. Int J Doc Anal Recognit (IJDAR) 13(2):121–131

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computational Sciences, Maharaja Ranjit Singh Punjab Technical University, Bathinda, Punjab, India

    Munish Kumar

  2. Department of Computer Science & Applications, Panjab University Regional Centre, Muktsar, Punjab, India

    M. K. Jindal

  3. Department of Computer Science & Engineering, Thapar Institute of Engineering & Technology, Patiala, Punjab, India

    R. K. Sharma

  4. Department of Computer Science & Engineering, Yadavindra College of Engineering, Talwandi Sabo, Bathinda, Punjab, India

    Simpel Rani Jindal

  5. Chitkara University Institute of Engineering and Technology Chitkara University, Chandigarh, Punjab, India

    Harjeet Singh

Authors
  1. Munish Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. K. Jindal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. R. K. Sharma
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Simpel Rani Jindal
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Harjeet Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Munish Kumar.

Ethics declarations

Conflict of interest

Authors have no conflict 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

Kumar, M., Jindal, M.K., Sharma, R.K. et al. Improved recognition results of offline handwritten Gurumukhi characters using hybrid features and adaptive boosting. Soft Comput 25, 11589–11601 (2021). https://doi.org/10.1007/s00500-021-06060-1

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-021-06060-1

Keywords

Search

Navigation