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%.
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
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
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
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
Freund Y, Schapire RE (1999) A short introduction to boosting. J Jpn Soc Artif Intell 14(5):771–780
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
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
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
Kaur H, Kumar M (2021) On the recognition of offline handwritten word using holistic approach and AdaBoost methodology. Multimed Tools Appl 80:11155–11175
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
Koundal K, Kumar M, Garg NK (2017) Punjabi optical character recognition: a survey. Indian J Sci Technol 10(19):1–8
Kumar M, Sharma RK, **dal MK (2013a) A novel feature extraction technique for offline handwritten Gurumukhi character recognition. IETE J Res 59(6):687–692
Kumar M, **dal MK, Sharma RK (2013b) MDP Feature extraction technique for offline handwritten Gurumukhi character recognition. Smart Comput Rev 3(6):397–404
Kumar M, Sharma RK, **dal MK (2014) A novel hierarchical technique for offline handwritten Gurumukhi character recognition. Natl Acad Sci Lett 37(6):567–572
Kumar M, **dal 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
Kumar M, **dal MK, Sharma RK, **dal 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
Kumar M, **dal SR, **dal 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
Kumar M, **dal MK, Sharma RK, **dal 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
Kumar M, **dal 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, **dal 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
Lehal GS, Singh C (1999) Feature extraction and classification for OCR of Gurumukhi script. Vivek 12(2):2–12
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
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
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
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
Shahin AA (2017) Printed Arabic text recognition using linear and non-linear regression. Int J Adv Comput Syst Appl 8(1):227–235
Sharma DV, Jain U (2010) Recognition of isolated handwritten characters of Gurumukhi script using neocognitron. Int J Comput Appl 10(8):10–16
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
Singh P, Budhiraja S (2012) Offline handwritten Gurumukhi numeral recognition using wavelet transforms. Int J Mod Educ Comput Sci 8:34–39
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
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
Yuan J, **ong H-C, **ao 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
Zhang TY, Suen CY (1984) A fast parallel algorithm for thinning digital patterns. Commun ACM 27(3):236–239
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
Author information
Authors and Affiliations
Corresponding author
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
About this article
Cite this article
Kumar, M., **dal, 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
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-021-06060-1