Abstract
Pattern Recognition is the method of mapping the inputs to their respective target classes based on features of data. In this paper a stacked ensemble meta-learning approach for customized convolutional neural network is proposed for Marathi handwritten numeral recognition. Stacked ensemble merges the pre-trained base pipe lines to create a multi-head meta-learning classifier that outputs the final target labels. It overpowers the average ensemble because the weighted and maximum contribution of each pipeline is taken in this approach. The stacked ensemble meta-learning classifier proves to be efficient because the base pipelines, which are already acquainted with output desirable results, are concatenated, instead of averaging, to achieve maximum efficiency. Performance evaluation and analysis have been done on Marathi handwritten numeral dataset, and the experiment results are better than the existing proposed systems.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Find the latest articles, discoveries, and news in related topics.References
Sharma N, Pal U, Kimura F, Pal S (2009) Recognition of off-line handwritten Devanagari characters using quadratic classifier. In: Proceedings of ICVGIP, vol 31. Springer, 444–457
Bhattacharya U, Chaudhuri BB (2006) Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE Trans Pattern Recognit Mach Intell 4338:805–816
Bhattacharya U, Shridhar M, Parui SK, Sen PK, Chaudhuri BB (2012) Offline recognition of handwritten Bangla characters: an efficient two-stage approach. Pattern Anal Appl 15:445–458
Dongre VJ, Mankar VH (2013) Devnagari handwritten numeral recognition using geometric features and statistical combination classifier. Int J Comput Sci Eng 2:856–863
Kim KM, Park JJ, Song YG, Kim IC, Suen CY (2004) Recognition of handwritten numerals using a combined classifier with hybrid features. In: SSPR and SPR. Springer, 992–1000
Acharya DU, Subba Reddy NV, Makkithaya K (2008) Multilevel classifiers in recognition of handwritten Kannada numerals. World Acad Sci Eng Technol 42:278–283
Vasantha C, Jain R, Patvardhan (2008) Fast and robust scheme for recognition of handwritten Devnagri Numerals. In: National System Conference, IIT Roorkee, pp 1–7
Kumar R, Vashishtha A, Agrawal I (2014) Devanagari handwritten numerals recognition based on invariant moments. Int J Comput Sci Manag Stud 14(6):8–11
Singh R, Yadav CS, Verma P, Yadav V (2010) Optical character recognition (OCR) for printed Devnagari script using artificial neural network. Int J Comput Sci Commun 1(1):91–95
Rajput GG, Mali SM (2010) Fourier descriptor based isolated Marathi handwritten numeral recognition. Int J Comput Appl 7:1–5
Bhattacharya U, Parui SK, Shaw B, Bhattacharya K (2006) Neural Combination of ANN and HMM for handwritten Devanagari numeral recognition. Tenth international workshop on frontiers in handwriting recognition. La Baule, France, pp 613–618
Srivastava SK, Gharde SS (2010) Support vector machine for handwritten Devanagri numeral recognition. Int J Comput Appl 7:9–14
Mane DT, Kulkarni UV (2018) Visualizing and understanding customized convolutional neural network for recognition of handwritten Marathi numerals. Procedia Comput Sci 132:1123–1137
Mane DT, Kulkarni UV (2017) A survey on supervised convolutional neural network and its major applications. Int J Rough Sets Data Anal 4(3):71–82
Vaidya MV, Joshi YV (2015) Marathi numeral recognition using statistical distribution features. In: International Conference on Information Processing, Pune, India, pp 586–591
Hanmandlu M, Murthy OV, Madasu V (2008) Fuzzy model based recognition of handwritten Hindi characters. J Pattern Recognit Res 2:454–461
Khanale PB, Chitnis SD (2011) Handwritten Devanagari character recognition using artificial neural network. J Artif Intell 4(1):55–62
Patil S, Sinha GR (2012) Real time handwritten Marathi numerals recognition using neural network. Int J Inf Technol Comput Sci 4(12):76–81
Prashanth DS, Mehta RVK, Sharma N (2020) Classification of Handwritten Devanagari Number-An analysis of Pattern Recognition Tool using Neural Network and CNN. Procedia Comput Sci 167:2445–2457
Kadam AA, Bhalerao MV, Tanurkar MN (2019) Handwritten Marathi compound character reconition. Int J Eng Res Technol 8
Chikmurge D, Shriram R (2019) Marathi handwritten character recognition using SVM and KNN classifier. Hybrid Intell Syst HIS 2019:319–327
Ramteke S, Gurjar A, Deshmukh DS (2019) A Novel Weighted SVM Classifier Based on SCA for Handwritten Marathi Character Recognition. IETE J Res 1–13. https://doi.org/10.1080/03772063.2019.1623093
Mahapatra D, Choudhury C, Karsh RK, (2020) Handwritten character recognition using KNN and SVM based classifier over feature vector from autoencoder. In: Machine learning, image processing, network security and data sciences, MIND, (2020) Communications in computer and information science, vol 1240. Springer, Singapore, pp 304–317
Patil Y, Bhilare A (2019) Digits recognition of marathi handwritten script using LSTM neural network. In: Proceedings of the 5th international conference on computing, communication, control and automation, Pune, India, pp 1–4
Gupta D, Bag S (2021) CNN-based multilingual handwritten numeral recognition: a fusion-free approach. Expert Syst Appl 165:
Yann L, Yoshua G, Hinton G (2008) Deep learning. Nature 521:436–444
Mali SM (2012) Moment and density based handwritten Marathi numeral recognition. Indian J Comput Sci Eng 3(5):707–712
Patil PM, Sontakke TR (2007) Rotation, scale and translation invariant handwritten Devanagari numeral character recognition using general fuzzy neural network. Pattern Recognit 40:2110–2117
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mane, D.T., Tapdiya, R. & Shinde, S.V. Handwritten Marathi numeral recognition using stacked ensemble neural network. Int. j. inf. tecnol. 13, 1993–1999 (2021). https://doi.org/10.1007/s41870-021-00723-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41870-021-00723-w