Character recognition creates an increasing demand on various evolving applications areas and methodologies of image processing in order to effectively recognize text of each script. It is considered as common method of digitizing an image in order to gather text of image more efficiently. The stages of character recognition include pre-processing, segmentation, feature extraction, classification and post processing. It has been noticed that there exist numerous languages such as Marathi, Gujarati, Gurumukhi, Arabic, Modi etc. where stages of character recognition lays important role for recognition of text image. Pre-processing and segmentation are considered as two crucial stages of character recognition with the purpose of providing smooth and clean image for further processing. These stages help in enhancing color format, to maintain skew angle of images, compresses size of image, separates line word and characters from images etc. A comparative study of various sub stages of pre-processing and segmentation is performed based on some parameters such as data type, window size, recognition rate, sample size, and so on. These parameters help in improving quality of image in order to achieve successful recognition rate.

Character recognition, binarization, noise reduction, segmentation, compression, normalization

[1] R. Mithe, S. Indalkar and N. Divekar, “Optical Character Recognition”, International Journal of Recent Technology and Engineering, Vol. 2, No.1, pp. 2277-3878, 2013.
[2] R. Palmondon and S. N. Srihari, “Online and Offline Handwritten Recognition: A Comprehensive Survey”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No.1, pp. 63-84, 2000.
[3] M. Kasthuri and V. Shanthi, “Noise Reduction and Pre-processing techniques in Handwritten Character Recognition”, International Journal of Computing Science and Communication Technologies, Vol. 6, No. 2, 2014.
[4] J. Shi, N. Ray and H. Zhang, “Shape Based Local Thresholding for Binarization of Document Images”, Elsevier Journal of Pattern Recognition on Letters, Vol. 33, Issue 1, pp. 24-32, 2012.
[5] T. Sari, L. Souici and M. Selami, “Off-line Handwritten Arabic Character Segmentation Algorithm: ACSA”, IEEE, 2007.
[6] M. S. Das, C. R. K. Reddy, A Govardhan and G. Saikrishna, “Segmentation of Overlapping Text Lines, Characters in Printed Telugu Text Document Images”, International Journal of Engineering Science and Technology, Vol. 2, No.11, pp. 6606-6610, 2010.
[7] P. Stathis, E. Kavallieratou and N. Papamarkos, “An Evaluation Survey of Binarization Algorithms on Historical Documents”, IEEE, 2008.
[8] D. S. Guru, M. Ravikumar and S. Manjunath, “Multiple Skew Estimation in Multilingual Handwritten Documents”, International Journal of Computer Science, Vol. 10, No. 2, pp. 1694-0814, 2013.
[9] P. Poovizhi, “A Study on Preprocessing Techniques for the Character Recognition”, International Journal of Open Information Technologies, Vol. 2, No. 12, pp. 2307-8162, 2014.
[10] N. Attlas and Dr. Sheifali Gupta, “Wavelet Based Techniques for Speckle Noise Reduction in Ultrasound Images”, International. Journal of Engineering Research and Applications, Vol. 4, Issue 2, pp.508-513, 2014.
[11] D.Maheswari and Dr.V.Radha, “Noise Removal in Compound Image using Median Filter”, International Journal on Computer Science and Engineering, Vol. 2, No. 4, pp.1359-1362, 2010.
[12] T. Gebreyohannes and D. Y. Kim, “Adaptive Noise Reduction Scheme for Salt and Pepper”, 2012.
[13] V. Murugan, T. Avudaiappan and Dr. R. Balasubramanian, “A Comparative Analysis of Impulse Noise Removal Techniques on Gray Scale Images”, International Journal of Signal Processing, Image Processing and Pattern Recognition, Vol. 7, No.5, pp.239-248, 2014.
[14] C. Mythili and V. Kavitha, “Efficient Technique for Color Image Noise Reduction”, ACM Proceeding on The Research Bulletin of Jordan, Vol. 2, Issue 3, 2011.
[15] Y. Yang and H. Yan, “An Adaptive Logical Method for Binarization of Degraded Document Images”, Elsevier Journal on Pattern Recognition, Vol. 33, Issue 5, pp.787-807, 2000.
[16] Amjad Rehman Khan & Dzulkilfli Muhammad, “A Simple Segmentation Approach for Unconstrained Cursive Handwritten Words in Conjunction with the Neural Network”, International Journal of Image Processing, 2008.
[17] D.N. Basekar, “Special Approach for Recognition of Handwritten MODI Script’s Vowels”, International Journal of Computer Applications, 2012.
[18] H. R. Thaker and C. K. Kumbharana, “Preprocessing and Segregating Offline Gujarati Handwritten Datasheet for Character Recognition”, International Journal of Computer Applications, Vol. 97, No. 18, pp. 0975-8887, 2014.
[19] T. Nawaz, S. A. H. S. Naqvi, H. Rehman and A. Faiz, “Optical Character Recognition System for Urdu Using Pattern Matching Technique”, International Journal of Image Processing, Vol. 3, Issue 3, 2009.
[20] GajananBirajdar and MansiSubhedar, “Use of JPEG Algorithm in Handwritten Devanagari Numeral Recognition”, International Journal of Distributed and Parallel Systems ,Vol. 2, No. 4, 2011.
[21] P. Haffner, L. Bottou, P.G. Howard, and YannLeCun, “DjVu: Analyzing and Compressing Scanned Documents for Internet Distribution”, International Conference Document Analysis and Recognition, 2008.
[22] S. V. Khangar and L.G. Malik, “Compression of Scan Digitized Handwritten Text for Indian Language Document”, Internatioanl Conference on Advances in Computer, Electronics and Electrical Engineering, 2012.
[23] C. L. Liu, M. Koga, H. Sako and H. Fujisawa, “Aspect Ratio Adaptive Normalization for Handwritten Character Recognition”, Springer Conference on Advances in Multimodal Interfaces, 2000.
[24] A. Vinciarelli and J. Luettin, “A New Normalization Technique for Cursive Handwritten Words”, Elsevier Journal on Pattern Recognition Letters, Vol. 22, pp. 1043-1050, 2001.
[25] T.Abu-Ain, S.N. H. Sheikh Abdullah, K. Omar, A. Abu-Ein , B. Bataineh and W. Abu-Ain, “Text Normalization Method for Handwritten Script”, Vol. 7, No. 2, pp. 164-175, 2013.
[26] L. Shah, R. Patel, S.Patel and J. Maniar, “Skew Detection and Correction for Gujarati Printed and Handwritten Character using Linear Regression”, International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 4, Issue 1, 2014.
[27] M.L.M Karunanayaka, C.A Marasinghe and N.D Kodikara, “Thresholding, Noise Reduction and Skew correction of Sinhala Handwritten Words”, IAPR Conference on Machine VIsion Applications, May 2005.
[28] Nandini N., Srikanta Murthy K., and G. Hemantha Kumar, “Estimation of Skew Angle in Binary Document Images Using Hough Transform”, World Academy of Science, Engineering and Technology, Vol. 18, pp. 06-23,2008.
[29] G.S Lehal and C. Singh, “A Technique for Segmentation of Gurmukhi Text”, International Journal of Computer Applications, 2002.
[30] R. K. Sharma and A. Singh, “Segmentation of Handwritten Text in Gurmukhi Script”, International Journal of Image Processing, Vol.3, No.2, 2008.
[31] S. Aman and S. Gupta, “An Approach for Recognizing Modi Lipi using Ostu’s Binarization Algorithm and Kohenen Neural Network”, International Journal of Computer Applications, Vol. 111, No. 2, February 2015.
[32] V. Saraf and D.S. Rao, “Devnagari Script Character Recognition Using Genetic Algorithm for Get Better Efficiency”, International Journal of Soft Computing and Engineering, Vol. 2, Issue. 4, 2013.
[33] C. Silva and C. Kariyawasam, “Segmenting Sinhala Handwritten Characters”, International Journal of Conceptions on Computing and Information Technology, Vol. 2, Issue. 4, 2014.
[34] M. Sarfraz, S.N. Nawaz and A. Al-Khuraidly, “Offline Arabic Text Recognition system”, IEEE Internatioanl Conference on geometric Modeling and Graphics, August 2003.
[35] R. J. Rodrigues and A.G.C Thome, “Cursive Character Recognition- A Character Segmentation Method Using Projection Profile-Based Technique”, 2002.
[36] G. S. Rao, M. Imanuddin and B. H. Kumar, “Script Identification of Telugu, English and Hindi Document Image”, International Journal of Advanced Engineering and Global Technology, Vol. 2, No. 2, pp. 2309-4893, 2014.
[37] P.P. Roy, U. Pal and JosepLlados, “Morphology Based Handwritten Line Segmentation Using Foreground and Background Information”, International Journal of Computer Applications, 2011.
[38] S. Osher and R. Fedkiw, “Level Set Methods and Dynamic Implicit Surfaces”, Springer, 2000.
[39] Y. Li, Y. Zheng, and D. Doermann, “Detecting Text Lines in Handwritten Documents,”International Conference on Pattern Recognition, pp. 1030–1033, 2006.
[40] M. Kumar, R. K. Sharma and M. K. Jindal, “Segmentation of Lines and Words in Handwritten Gurmukhi Script Documents”, ACM Proceeding on Intelligent Interactive Technologies and Multimedia, Vol. 1, Allahabad, 2010.
[41] A. Cheung, M. Bennamoun and N.W. Bergmann, “An Arabic Optical Character Recognition System using Recognition-Based Segmentation”, Elsevier, Pattern Recognition, pp. 215-233, 2001.
[42] S. Al-Ma’adeed, D. Elliman, and C. Higgins, “A Data Base for Arabic Handwritten Text Recognition Research”, International Arab Journal of Information Technology, 2004.
[43] G. Bansal, D. Sharma”, “Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script”, International Journal of Computer Applications, Vol. 1, No. 24, pp. 0975 – 8887, 2010.
[44] S. Wshah, Z. Shi and V.Govindaraju, “Segmentation of Arabic Handwriting based on both Contour and Skeleton Segmentation”, International Conference on Document Analysis and Recognition, 2009.