Skip to main content
SpringerLink
Log in

Genetic Algorithm Based Global and Local Feature Selection Approach for Handwritten Numeral Recognition

  • Chapter
  • First Online:
Metaheuristics in Machine Learning: Theory and Applications

Part of the book series: Studies in Computational Intelligence ((SCI,volume 967))

Abstract

Although various methods have been proposed by the researchers over the years to carry out isolated handwritten numeral recognition, this is still considered as a challenging research problem. The primary challenge occurs because of sizable differences in writing styles of the digit patterns. Literature reveals that several feature extraction and classification methods have been researched upon to optimize the said recognition system but there is still room for improvement. Here, we introduce a two-stage handwritten numeral recognition system for three most popular scripts used in Indian subcontinent—Devanagari, Bangla and Roman. Initially, the global features that are estimated based on Histogram of Oriented Gradients (HOG) feature descriptor help in the formation of inter-numeral groups having nearly similar structure. Then, the optimal subset of features is selected using Genetic Algorithm (GA) on the combination of HOG and local distance features. These optimal features, thus produced, are employed for the classification of handwritten digits within the intra-numeral groups. Finally, the Multi-layer Perceptron (MLP) classifier is used to recognize the numerals. The strength of the present approach is efficient feature selection and the comprehensive classification scheme due to which notable recognition accuracies have been attained which are found to be better than some previous approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 139.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 179.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 179.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. R. Hussain, A. Raza, I. Siddiqi, K. Khurshid, C. Djeddi, A comprehensive survey of handwritten document benchmarks: structure, usage and evaluation. EURASIP J. Image Video Process. 2015(1), 46 (2015)

    Article  Google Scholar 

  2. U. Bhattacharya, B.B. Chaudhuri, Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE Trans. Pattern Anal. Mach. Intell. 31(3), 444–457 (2008)

    Article  Google Scholar 

  3. U. Pal, N. Sharma, T. Wakabayashi, F. Kimura, Handwritten numeral recognition of six popular Indian scripts, in Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2. (IEEE, 2007), pp. 749–753

    Google Scholar 

  4. R.M. Bozinovic, S.N. Srihari, Off-line cursive script word recognition. IEEE Trans. Pattern Anal. Mach. Intell. 11(1), 68–83 (1989)

    Article  Google Scholar 

  5. P.K. Wong, C. Chan, Off-line handwritten Chinese character recognition as a compound Bayes decision problem. IEEE Trans. Pattern Anal. Mach. Intell. 20(9), 1016–1023 (1998)

    Article  Google Scholar 

  6. U. Pal, B.B. Chaudhuri, Indian script character recognition: a survey. Pattern Recogn. 37(9), 1887–1899 (2004)

    Article  Google Scholar 

  7. S. Basu, N. Das, R. Sarkar, M. Kundu, M. Nasipuri, D.K. Basu, An MLP based approach for recognition of handwritten Bangla’ numerals. arXiv preprint arXiv:1203.0876

  8. Y. Wen, L. He, A classifier for Bangla handwritten numeral recognition. Exp. Syst. Appl. 39(1), 948–953 (2012)

    Article  Google Scholar 

  9. M.K. Nasir, M.S. Uddin, Hand written Bangla numerals recognition for automated postal system. IOSR J. Comput. Eng. (IOSR-JCE) 8(6), 43–48 (2013)

    Google Scholar 

  10. O. Surinta, L. Schomaker, M. Wiering, A comparison of feature and pixel-based methods for recognizing handwritten bangla digits, in 2013 12th International Conference on Document Analysis and Recognition (IEEE, 2013), pp. 165–169

    Google Scholar 

  11. H.A. Khan, A. Al Helal, K.I. Ahmed, Handwritten Bangla digit recognition using sparse representation classifier, in 2014 International Conference on Informatics, Electronics and Vision (ICIEV) (IEEE, 2014), pp. 1–6

    Google Scholar 

  12. M.A.H. Akhand, M. Ahmed, M.H. Rahman, Convolutional neural network based handwritten Bengali and Bengali–English mixed numeral recognition. Int. J. Image Graph. Sig. Process. 8(9), 40 (2016)

    Google Scholar 

  13. P.K. Singh, R. Sarkar, M. Nasipuri, A comprehensive survey on Bangla handwritten numeral recognition. Int. J. Appl. Pattern Recogn. 5(1), 55–71 (2018)

    Article  Google Scholar 

  14. I.K. Sethi, B. Chatterjee, Machine recognition of constrained hand printed Devanagari. Pattern Recogn. 9(2), 69–75 (1977)

    Article  Google Scholar 

  15. U. Bhattacharya, B.B. Chaudhuri, R. Ghosh, M. Ghosh, On recognition of handwritten Devnagari numerals, in Proceedings of the Workshop on Learning Algorithms for Pattern Recognition (in conjunction with the 18th Australian Joint Conference on Artificial Intelligence), Sydney, p. 1–7 (2005)

    Google Scholar 

  16. M. Hanmandlu, O.R. Murthy, Fuzzy model based recognition of handwritten numerals. Pattern Recogn. 40(6), 1840–1854 (2007)

    Article  Google Scholar 

  17. M.J.K. Singh, R. Dhir, R. Rani, Performance comparison of devanagari handwritten numerals recognition. Int. J. Comput. Appl. 22 (2011)

    Google Scholar 

  18. A. Aggarwal, R.R. Renudhir, Recognition of Devanagari handwritten numerals using gradient features and SVM. Int. J. Comput. Appl. 48(8), 39–44 (2012)

    Google Scholar 

  19. P. Singh, A. Verma, N.S. Chaudhari, Handwritten Devnagari digit recognition using fusion of global and local features. Int. J. Comput. Appl. 89(1) (2014)

    Google Scholar 

  20. S. Prabhanjan, R. Dinesh, Handwritten devanagari characters and numeral recognition using multi-region uniform local binary pattern. Int. J. Multimedia Ubiquit. Eng. 11(3), 387–398 (2016)

    Article  Google Scholar 

  21. P.K. Singh, S. Das, R. Sarkar, M. Nasipuri, Recognition of offline handwriten Devanagari numerals using regional weighted run length features, in 2016 International Conference on Computer, Electrical and Communication Engineering (ICCECE) (IEEE, 2016), pp. 1–6

    Google Scholar 

  22. J. Cao, M. Ahmadi, M. Shridhar, Recognition of handwritten numerals with multiple feature and multistage classifier. Pattern Recogn. 28(2), 153–160 (1995)

    Article  Google Scholar 

  23. B.K. Prasad, G. Sanyal, A hybrid feature extraction scheme for Off-line English numeral recognition, in International Conference for Convergence for Technology (IEEE, 2014), pp. 1–5

    Google Scholar 

  24. R. Salouan, S. Safi, B. Bouikhalene, Isolated handwritten Roman numerals recognition using methods based on radon, Hough transforms and Gabor filter. Int. J. Hybrid Inf. Technol. 8, 181–194 (2015)

    Google Scholar 

  25. B. El Qacimy, M.A. Kerroum, A. Hammouch, Feature extraction based on DCT for handwritten digit recognition. Int. J. Comput. Sci. Issues (IJCSI) 11(6), 27 (2014)

    Google Scholar 

  26. Y. LeCun, The MNIST database of handwritten digits (1998). http://yann.lecun.com/exdb/mnist/

  27. P.K. Singh, S. Das, R. Sarkar, M. Nasipuri, Recognition of handwritten Indic script numerals using Mojette transform, in Proceedings of the First International Conference on Intelligent Computing and Communication (Springer, Singapore, 2017), pp. 459–466

    Google Scholar 

  28. P.K. Singh, R. Sarkar, M. Nasipuri, A study of moment based features on handwritten digit recognition. Appl. Comput. Intell. Soft Comput. (2016)

    Google Scholar 

  29. P.K. Singh, S. Das, R. Sarkar, M. Nasipuri, Script invariant handwritten digit recognition using a simple feature descriptor. Int. J. Comput. Vis. Rob. 8(5), 543–560 (2018)

    Google Scholar 

  30. S. Ghosh, A. Chatterjee, P.K. Singh, S. Bhowmik, R. Sarkar, Language-invariant novel feature descriptors for handwritten numeral recognition. Vis. Comput. 2020 (2020). https://doi.org/10.1007/s00371-020-01938-x

  31. R. Samanta, S. Ghosh, A. Chatterjee, R. Sarkar, A novel approach towards handwritten digit recognition using refraction property of light rays. Int. J. Comput. Vis. Image Process. (IJCVIP) 10(3), 1–17 (2020)

    Article  Google Scholar 

  32. M. Ghosh, R. Guha, R. Mondal, P.K. Singh, R. Sarkar, M. Nasipuri, Feature selection using histogram-based multi-objective GA for handwritten Devanagari numeral recognition, in Intelligent Engineering Informatics (Springer, Singapore, 2018), pp. 471–479

    Google Scholar 

  33. R. Guha, M. Ghosh, P.K. Singh, R. Sarkar, M. Nasipuri, M-HMOGA: a new multi-objective feature selection algorithm for handwritten numeral classification. J. Intell. Syst. 29(1), 1453–1467 (2019)

    Article  Google Scholar 

  34. S. Ghosh, S. Bhowmik, K.K. Ghosh, R. Sarkar, S. Chakraborty, A filter ensemble feature selection method for handwritten numeral recognition. EMR 7213 (2016)

    Google Scholar 

  35. A. Roy, N. Das, R. Sarkar, S. Basu, M. Kundu, M. Nasipuri, An axiomatic fuzzy set theory based feature selection methodology for handwritten numeral recognition, in ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India, vol. I. (Springer, Cham ,2014), pp. 133–140

    Google Scholar 

  36. S. Sarkar, M. Ghosh, A. Chatterjee, S. Malakar, R. Sarkar, An advanced particle swarm optimization based feature selection method for tri-script handwritten digit recognition, in International Conference on Computational Intelligence, Communications, and Business Analytics (Springer, Singapore, 2018), pp. 82–94

    Google Scholar 

  37. S. Chakraborty, S. Paul, R. Sarkar, M. Nasipuri, Feature map reduction in CNN for handwritten digit recognition, in Recent Developments in Machine Learning and Data Analytics (Springer, Singapore, 2019), pp. 143–148

    Google Scholar 

  38. J. Mukhoti, S. Dutta, R. Sarkar, Handwritten digit classification in Bangla and Hindi using deep learning. Appl. Artif. Intell. 1–26 (2020)

    Google Scholar 

  39. A. Chatterjee, S. Malakar, R. Sarkar, M. Nasipuri, Handwritten digit recognition using DAISY descriptor: a study, in 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT) (2018), pp. 1-4

    Google Scholar 

  40. M. Diem, S. Fiel, A. Garz, M. Keglevic, F. Kleber, R. Sablatnig, ICDAR 2013 competition on handwritten digit recognition (HDRC 2013), in 2013 12th International Conference on Document Analysis and Recognition (IEEE, 2013), pp. 1422–1427

    Google Scholar 

  41. R.C. Gonzalez, R.E. Woods, Digital Image Processing, vol. I (Prentice-Hall, India, 1992)

    Google Scholar 

  42. N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 1. (IEEE, 2005), pp. 886–893

    Google Scholar 

  43. M. Srinivas, L.M. Patnaik, Genetic algorithms: a survey. Computer 27(6), 17–26 (1994)

    Article  Google Scholar 

  44. Y.L. Wu, C.Y. Tang, M.K. Hor, P.F. Wu, Feature selection using genetic algorithm and cluster validation. Exp. Syst. Appl. 38(3), 2727–2732 (2011)

    Article  Google Scholar 

  45. S. Basu, N. Das, R. Sarkar, M. Kundu, M. Nasipuri, D.K. Basu, Handwritten Bangla alphabet recognition using an MLP based classifier. arXiv preprint arXiv:1203.0882 (2012)

  46. Languages spoken by more than 10 million people. Encarta Encyclopedia. Retrieved 23 February 2018

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, 711103, West Bengal, India

    Sagnik Pal Chowdhury, Ritwika Majumdar & Sandeep Kumar

  2. Department of Information Technology, Jadavpur University, Jadavpur University Second Campus, Plot No. 8, Salt Lake Bypass, LB Block, Sector III, Salt Lake City, Kolkata, 700106, West Bengal, India

    Pawan Kumar Singh

  3. Department of Computer Science and Engineering, Jadavpur University, 188, Raja S.C. Mullick Road, Kolkata, 700032, West Bengal, India

    Ram Sarkar

Authors
  1. Sagnik Pal Chowdhury
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ritwika Majumdar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sandeep Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pawan Kumar Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ram Sarkar
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Computer Sciences Department, CUCEI, University of Guadalajara, Guadajalara, Jalisco, Mexico

    Diego Oliva

  2. Department of Computer Science, Faculty of Computers and Information, Minia University, Minia, Egypt

    Essam H. Houssein

  3. Computer Sciences Department, CUCEI, University of Guadalajara, Guadajalara, Jalisco, Mexico

    Salvador Hinojosa

Rights and permissions

Reprints and permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Chowdhury, S.P., Majumdar, R., Kumar, S., Singh, P.K., Sarkar, R. (2021). Genetic Algorithm Based Global and Local Feature Selection Approach for Handwritten Numeral Recognition. In: Oliva, D., Houssein, E.H., Hinojosa, S. (eds) Metaheuristics in Machine Learning: Theory and Applications. Studies in Computational Intelligence, vol 967. Springer, Cham. https://doi.org/10.1007/978-3-030-70542-8_30

Download citation

Publish with us

Policies and ethics

Search

Navigation