Advertisement

English Character Recognition Using Robust Back Propagation Neural Network

  • Shrinivas R. ZanwarEmail author
  • Abbhilasha S. Narote
  • Sandipan P. Narote
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1037)

Abstract

OCR deals with the handwritten or printed character recognition with the help of digital computers and soft computing. The scanned images of characters and numbers are used as input for system which is analyzed and transformed it into character codes, normally in ASCII format, which is taken for the data processing. Presently, there are lots of issues in recognition of characters and numbers, which can degrade the performance of the system in various ways. Mainly, the rate of recognition is not improved due to distributed neighborhood pixels of an image. Also, there are some techniques used for the OCR are having lack of contrast levels which is well known by fading of the image. So in this paper, the most important concern is to take such measures to enhance the performance of the system for automatic recognition of characters. Here, the operations are performed on the handwritten English alphabets. The dataset is selected from the Chars74K with different shapes and preprocessed it which deals with filtering and edge detection. Then, in the feature extraction process, features are extracted by using independent component analysis and swarm intelligence is used for feature vector selection. Classification of images are done with the back propagation neural network which gives an effective learning approach. The precise contribution which is evaluated in this research work is the uniqueness of classifications using a combination of the feature extraction and feature optimization (instance selection) using extraction of feature vectors. The performance of the developed system is measured in terms of recognition rate, sensitivity and specificity compared with the benchmark.

Keywords

Edge detection Feature extraction (Independent component analysis and Swarm intelligence) Backpropagation neural network 

Notes

Acknowledgment

The authors would like to express sincere gratitude to Dr. Ulhas B. Shinde, Principal, CSMSS, Chh. Shahu College of Engineering, Aurangabad, for his continuous support and encouragement to publish this article. They would also like to thank Mr. Devendra L. Bhuyar, Mr. Amit M. Rawate, Mr. Sanket R. Zanwar, and Mr. Ajit G. Deshmukh for their recurrent help in this work.

References

  1. 1.
    Chaudhary, S., Garg, S., Sathyaraj, R., Behera, A.: An approach for optical character recognition on grid infrastructure using Kohonen neural network. Int. J. Adv. Res. Comput. Sci. 8(3) (2017).  https://doi.org/10.26483/ijarcs.v8i3.3039
  2. 2.
    Ahlawat, D.: A review on character recognition using OCR algorithm. J. Netw. Commun. Emerg. Technol. (JNCET) 7(5), 56–61 (2017)Google Scholar
  3. 3.
    Gail, H.R., Hantler, S.L.: Method and apparatus for automatic detection of spelling errors in one or more documents. U.S. Patent 9,465,791, issued 11 October 2016Google Scholar
  4. 4.
    Schultz, S.: Method for the automatic material classification and texture simulation for 3D models, U.S. Patent 9,330,494, issued 3 May 2016Google Scholar
  5. 5.
    Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10(1), 19–36 (2016)CrossRefGoogle Scholar
  6. 6.
    Hamad, K.A., Kaya, M.: A detailed analysis of optical character recognition technology. Int. J. Appl. Math. Electron. Comput. 4(Special Issue–1), 244–249 (2016).  https://doi.org/10.18100/ijamec.270374CrossRefGoogle Scholar
  7. 7.
    Afroge, S., Raihan, M.A.: Optical character recognition using back propagation neural network. J. Image Process. Pattern Recognit. Prog. 11–18 (2016).  https://doi.org/10.1109/icecte.2016.7879615
  8. 8.
    Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: Proceedings of the IEEE Conference on CVPR, pp. 2231–2239 (2016).  https://doi.org/10.1109/cvpr.2016.245
  9. 9.
    Burry, A.M., Kozitsky, V., Paul, P.: License plate optical character recognition method and system, U.S. Patent 8,644,561, issued 4 February 2014. https://books.google.co.in/books?isbn=1118971647
  10. 10.
    Naz, S., Hayat, K., Razzak, M.I., Anwar, M.W., et al.: The optical character recognition of Urdu like cursive scripts. Pattern Recognit. 47(3), 1229–1248 (2014).  https://doi.org/10.1016/j.patcog.2013.09.037CrossRefGoogle Scholar
  11. 11.
    Longacre, J.A.: Method for omnidirectional processing of 2D images including recognizable characters: U.S. Patent 8,682,077, issued 25 March 2014. https://patents.justia.com/inventor/andrew-longacre-jr
  12. 12.
    Bhatia, E.N.: Optical character recognition techniques: a review. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 4(5) (2014). https://pdfs.semanticscholar.org/7ca5/584576423b366ad7bdf03d5fc136a2e958e6.pdf
  13. 13.
    Mohammad, F., Anarase, J., Shingote, M., Ghanwat, P.: Optical character recognition implementation using pattern matching. Int. J. Comput. Sci. Inf. Technol. 5(2), 2088–2090 (2014). https://doi.org/10.1.1.661.1089
  14. 14.
    Grimmer, J., Stewart, B.M.: Text as data: the promise and pitfalls of automatic content analysis methods for political texts. Polit. Anal. 21(3), 267–297 (2013).  https://doi.org/10.1093/pan/mps028CrossRefGoogle Scholar
  15. 15.
    Mithe, R., Indalkar, S., Divekar, N.: Optical character recognition. Int. J. Recent Technol. Eng. (IJRTE) 2(1), 72–75 (2013).  https://doi.org/10.1093/pan/mps028CrossRefGoogle Scholar
  16. 16.
    Kumar B., Kumar N., Palai C., et al.: Optical character recognition using ant miner algorithm: a case study on oriya character recognition. IJCA 61(3) (2013).  https://doi.org/10.5120/9908-4500CrossRefGoogle Scholar
  17. 17.
    Sharma, N., Kumar, B., Singh, V.: Recognition of off-line hand printed English characters, numerals and special symbols. In: IEEE International Conference Confluence The Next Generation Information Technology Summit, pp. 640–645 (2014).  https://doi.org/10.1109/confluence.2014.6949270
  18. 18.
    Santosh, K.C., Lamiroy, B., Wendling, L.: DTW-Radon-based shape descriptor for pattern recognition. Int. J. Pattern Recognit. Artif. Intell. (2013).  https://doi.org/10.1142/S0218001413500080MathSciNetCrossRefGoogle Scholar
  19. 19.
    Santosh, K.C., Wendling, L.: Character recognition based on non-linear multi-projection profiles measure. Front. Comput. Sci. 9(5), 678–690 (2014).  https://doi.org/10.1007/s11704-015-3400-2CrossRefGoogle Scholar
  20. 20.
    Santosh K.C.: Character recognition based on DTW-Radon. In: 11th International Conference on Document Analysis and Recognition - ICDAR 2011, September 2011, Beijing, China, pp. 264–268. IEEE Computer Society (2011).  https://doi.org/10.1109/ICDAR.2011.61
  21. 21.
    Ukil, S., Ghosh, S., Obaidullah, S.M., Santosh, K.C., Roy, K., Das, N.: Deep learning for word-level handwritten Indic script identification.  https://doi.org/10.1109/ReTIS.2015.7232880

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Shrinivas R. Zanwar
    • 1
    Email author
  • Abbhilasha S. Narote
    • 2
  • Sandipan P. Narote
    • 3
  1. 1.CSMSS, Chh. Shahu College of EngineeringAurangabadIndia
  2. 2.S.K.N.ś College of EngineeringPuneIndia
  3. 3.Governmentś Residence Women’s PolytechnicTasgaon, SangliIndia

Personalised recommendations