An Analysis of Some Pre-Processing Techniques useful in the Recognition of Offline Gujarati Handwritten Characters

Manish M. Kayasth*, 0**
* Assistant Professor and HOD, UCCC & SPBCBA & SDHG College of BCA and IT, Surat, India.
** Assistant Professor and I/c Principal, T. & M. T. College of Information Science, Surat, India.
Periodicity:December - February'2017
DOI : https://doi.org/10.26634/jit.6.1.13502

Abstract

Character Recognition wherein a computer is able to interpret human handwriting and recognize it as an alphanumeric character. The input provided to the recognition system is an image of a digit, a word, or generally combinations of such texts. The system accordingly generates an output as an ASCII transcription of the inputted text. This task involves a number of pre-processing steps. This paper analyses and mainly focuses on few pre-processing approaches to recognize handwritten Gujarati characters. The whole character recognition process is logically divided into separate parts like Image acquisition, Preprocessing, Processing, and Post-processing. In the targeted system which will be used to recognize character; the scanned image is first passed through pre-processing modules like Image Acquisition, Smoothing, Boundary tracing, etc., in order to achieve a higher recognition rate.

Keywords

Character Recognition, Gujarati Handwritten Characters, Filters, Image Smoothing, Boundary Tracing, Scaling

How to Cite this Article?

Manish M. Kayasth and Bharat C. Patel (2017). An Analysis of Some Pre-Processing Techniques useful in the Recognition of Offline Gujarati Handwritten Characters. i-manager’s Journal on Information Technology, 6(1), 1-7. https://doi.org/10.26634/jit.6.1.13502

References

[1]. Ambika Ramchandra, (2013). “Filters a Image Enhancement and Smoothing Technique”. Paripex – Indian Journal of Research, ISSN - 2250-1991, Vol. 2, No. 7, July 2013 pp. 31-33.
[2]. Chhaya Patel, and Apurva Desai, (2013). “Gujarati Handwritten Character Recognition using Hybrid Method based on Binary Tree-Classifier and K-Nearest Neighbour”. International Journal of Engineering Research & Technology (IJERT), ISSN: 2278-0181, Vol. 2, No. 6, pp. 2337-2345.
[3]. Leiming Sun, and Tianshun Huang, (2013). “A new boundary tracing algorithm of the contour of objects in the binary image”. Computer Modeling & New Technologies, Vol.17, No.5A, pp. 63-67.
[4]. Manish Kayasth, and Bankim Patel, (2009). “Offline typed Gujarati Character Recognition”. National Journal of System and Information Technology, ISSN: 0974-3308, Vol. 2, No. 1, pp. 73-82.
[5]. Manish Kayasth, and Bankim Patel, (2008). “A Preliminary Analysis on Issues and Challenges for the Handwritten Text Recognition of Gujarati Language”. Proceedings of the National Conference on Innovative Dimension for Business and Information Technology, ISBN: 978-81-906446-0-2, Pub. SRIMCA, pp. 57-60.
[6]. Manish Kayasth, (2006). “Study of Various Character Recognition Algorithms”. National Conference on Intelligent Information Retrieval & Processing, Pub. SRIMCA.
[7]. K. Siva Praveen et al., (2016). “Implementation of Image Sharpening and smoothing using Filters”. International Journal of Scientific Engineering and Applied Science (IJSEAS), ISSN: 2395-3470, Vol. 2, No. 1, pp. 7-14.
[8]. Tech-Algorithm.com (2007). Nearest Neighbor Image Scaling. Retrieved from http://tech-algorithm.com /articles/nearest-neighbor-image-scaling/
[9]. Digital Image Processing, (n.d.). Spatial domain filtering, Part I. Retrieved from https://sisu.ut.ee/image processing/book/8
[10]. Erik Smistad.no, (2016). Moore Neighbor Contour Tracing Algorithm in C++. Retrieved from https://www. eriksmistad.no/moore-neighbor-contour-tracingalgorithm- in-c
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.