Abstract

Ability of a computer to recognize handwritten character is a fascinating area of research due to the peculiarities involved in handwritten characters. Algorithm for Offline handwritten Character recognition differs as a result of diversities involved in writing with various language script. In a task of handwritten character recognition preprocessing and segmentation are two main phases and preliminary steps to be performed on acquired handwritten images. Achieving higher performance in handwritten character recognition depends on feature extraction process, which is highly influenced by preprocessing phase. Proposed work is a first step into an area of offline handwritten Gujarati character recognition. This paper presents algorithm for preprocessing image making it noise free and extracting region of interest for character recognition, segregating datasheet containing 30 characters written in Gujarati script to thirty different images having isolated characters. Further results obtained by employing proposed algorithm is discussed in this paper.

References

• K. K. M. BAHETI M. J. , "Comparison Of Classifiers For Gujarati Numeral Recognition," International Journal of Machine Intelligence, vol. 3, no. 3, pp. 160-163, 2011.
• A. A. Desai, "Gujarati handwritten numeral optical character reorganization through neural network," Pattern Recognition, vol. 43, 2010.
• R. M. H. K. B. Dhandra, "Telugu and Devanagari Handwritten Numeral Recognition with Probabilistic Neural Network?: A Novel Approach, Architecture," pp. 83-88, 2010.
• M. f. Kamal moro, "Gujarati Handwritten Numeral Optical Character through neural network and skeletonization," jurnal of sistem komputer, vol. 3, no. 1, pp. 40-43, 2013.
• K. D. N. Shanthi, "A novel SVM-based handwritten Tamil character recognition system," pp. 173-180.
• J. Prasad, U. Kulkarni and R. Prasad, "Template Matching Algorithm for Gujarati Character," in In Proc. Of 2nd International Conference on Emerging Trends in Engineering and Technology (ICETET), 2009.
• J. Prasad, U. Kulkarni and R. Prasad, "Offline Handwritten Character Recognition of Gujarati script using Pattern Matching," in In Proc. Of 3rd International Conference on Anti-counterfeiting, Security, and Identification in Communication, 2009.
• K. K. V. Baheti M. J, "Recognition of Gujarati Numerals using Hybrid Approach and Neural Networks," in International Journal of Computer Applications, 2013.
• "http://nf. nci. org. au/facilities/software/Matlab/toolbox /images/rgb2gray. html," [Online].
• L. G. &. S. G. C. Shapiro, "Computer Vision," Prentice , 2002.
• M. S. a. B. Sankur, "Survey over image thresholding techniques and quantitative performance evaluation," Journal of Electronic Imaging, vol. 13, no. 1, p. 146–165, 2004.
• "http://www. cse. unr. edu/~bebis/CS791E/Notes/Thresho lding. pdf," [Online].
• "http://imageprocessingblog. com/histogram-adjustments-in-matlab-part-ii-equalization/," [Online].
• http://www. mathworks. in/help/images/ref/im2bw. html" [Online].