Abstract
This paper presents a novel HNR system based on the hypothesis of human learning of writing. Superposition of different shaped, sized and oriented handwritten numerals into same-sized printed form will make recognition task easy because classifier has to classify a small set of fixed patterned printed images leading to improvement of recognition accuracy. A modified version of convolutional auto-encoder (CAE) has been utilized as superposition method to transform images of handwritten numeral into printed numeral, while convolutional neural network (CNN) is used as a classifier to recognize the printed numeral. The efficiency of the proposed system is tested on Bengali numerals owing to achieve fair recognition performance because the recognition accuracy of Bengali HNR is still relatively low and remains an open research challenge.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22:63–84. https://doi.org/10.1109/34.824821
Wen Y, Lu Y, Shi P (2007) Handwritten Bangla numeral recognition system and its application to postal automation. Pattern Recogn 40:99–107. https://doi.org/10.1016/j.patcog.2006.07.001
Das N, Sarkar R, Basu S, Kundu M, Nasipuri M, Basu DK (2012) A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application. Appl Soft Comput 12:1592–1606. https://doi.org/10.1016/j.asoc.2011.11.030
Nasir MK (2013) Hand written Bangla numerals recognition for automated postal system. IOSR J Compu. En. 8:43–48. https://doi.org/10.9790/0661-0864348
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24:509–522. https://doi.org/10.1109/34.993558
Khan MMR, Shah MdAR, Alam MM (2004) Bangla handwritten digits recognition using evolutionary artificial neural networks. In: 7th international conference on computer and information technology (ICCIT 2004), pp. 26–28, Dhaka
Akhand MAH, Ahmed M, Rahman MMH (2016) Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition. Int J Image Graph Signal Process 8:40–50. https://doi.org/10.5815/ijigsp.2016.09.06
Oval SG, Shirawale S (2015) Recognizing handwritten Devanagari words using recurrent neural network. Presented at the (2015). https://doi.org/10.1007/978-3-319-12012-6_45
Akhand MAH, Ahmed M, Rahman MMH, Islam MM (2018) Convolutional neural network training incorporating rotation-based generated patterns and handwritten numeral recognition of major Indian scripts. IETE J Res 64:176–194. https://doi.org/10.1080/03772063.2017.1351322
Labusch K, Barth E, Martinetz T (2008) Simple method for high-performance digit recognition based on sparse coding. IEEE Trans Neural Netw 19:1985–1989. https://doi.org/10.1109/TNN.2008.2005830
Ranzato M, Huang FJ, Boureau Y-L, LeCun Y (2007) Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: 2007 IEEE conference on computer vision and pattern recognition. IEEE, pp 1–8. https://doi.org/10.1109/CVPR.2007.383157
Chan T-H, Jia K, Gao S, Lu J, Zeng Z, Ma Y (2015) PCANet: a simple deep learning baseline for image classification? IEEE Trans Image Process 24:5017–5032. https://doi.org/10.1109/TIP.2015.2475625
Jia Y, Huang C, Darrell T (2012) Beyond spatial pyramids: receptive field learning for pooled image features. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3370–3377. https://doi.org/10.1109/CVPR.2012.6248076
Calderón A, Roa Ovalle S, Victorino J (2003) Handwritten digit recognition using convolutional neural networks and gabor filters. In: Proceedings of the international congress on computational intelligence CIIC
Le QV, Ngiam J, Lahiri A, Prochnow B, Ng AY (2011) On optimization methods for deep learning. In: ICML’11 proceedings of the 28th international conference on international conference on machine learning, pp 265–272, Bellevue, Washington, USA
Pal U, Chaudhuri BB, Belaid A (2006) A complete system for Bangla handwritten numeral recognition. IETE J Res 52:27–34. https://doi.org/10.1080/03772063.2006.11416437
Basu S, Sarkar R, Das N, Kundu M, Nasipuri M, Basu DK (2005) Handwritten Bangla digit recognition using classifier combination through DS technique. Presented at the (2005). https://doi.org/10.1007/11590316_32
Bhattacharya U, Chaudhuri BB (2009) Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE Trans Pattern Anal Mach Intell 31:444–457. https://doi.org/10.1109/TPAMI.2008.88
Ahmed M, Paul AK, Akhand MAH (2016) Stacked auto encoder training incorporating printed text data for handwritten bangla numeral recognition. In: 2016 19th international conference on computer and information technology (ICCIT). IEEE, pp 437–442. https://doi.org/10.1109/ICCITECHN.2016.7860238
Wen Y, He L (2012) A classifier for Bangla handwritten numeral recognition. Expert Syst Appl 39:948–953. https://doi.org/10.1016/j.eswa.2011.07.092
Shopon M, Mohammed N, Abedin MA (2016) Bangla handwritten digit recognition using autoencoder and deep convolutional neural network. In: 2016 international workshop on computational intelligence (IWCI). IEEE, pp 64–68. https://doi.org/10.1109/IWCI.2016.7860340
Bashar MdR, Rashidul Hasan MAFM, Hossain MdA, Das D (2004) Handwritten Bangla numerical digit recognition using histogram technique. Asian J Inf Technol 3:611–615. https://doi.org/ajit.2004.611.615
Bhattacharya U, Chaudhuri B (2009) Offline handwritten Bangla and Devanagari numeral databases. Kolkata: computer vision and pattern recognition unit. Indian Statistical Institute. http://www.isical.ac.in/»ujjwal/download/database.html
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shuvo, M.I.R., Akhand, M.A.H., Siddique, N. (2020). Handwritten Numeral Superposition to Printed Form Using Convolutional Auto-Encoder and Recognition Using Convolutional Neural Network. In: Uddin, M.S., Bansal, J.C. (eds) Proceedings of International Joint Conference on Computational Intelligence. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-15-3607-6_14
Download citation
DOI: https://doi.org/10.1007/978-981-15-3607-6_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3606-9
Online ISBN: 978-981-15-3607-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)