A novel clustering based fuzzy approach for character segmentation in handwritten odia scripts

Character Segmentation is a pivotal decisive component in Natural Language Processing that seeks to dissolve an image of an array of characters into sub-images of distinct symbols. Literature survey reveals that very little work has been reported in character segmentation of handwritten Odia documents. In this paper, a novel clustering based Fuzzy schema is presented for segmentation of characters in unconstrained Odia language. The simulation based experiments of proposed methodology are conducted on transcribed Odia scripts. It is observed that the segmentation performance in terms of Success Rate and F-Measure parameters is superior to the other existing state of the art segmentation techniques.

[1]  Subhadip Basu,et al.  A Fuzzy Technique for Segmentation of Handwritten Bangla Word Images , 2007, 2007 International Conference on Computing: Theory and Applications (ICCTA'07).

[2]  Georgi Gluhchev,et al.  Handwritten document image segmentation and analysis , 1993, Pattern Recognit. Lett..

[3]  Sargur N. Srihari,et al.  A statistical approach to line segmentation in handwritten documents , 2007, Electronic Imaging.

[4]  Laurence Likforman-Sulem,et al.  Text line segmentation of historical documents: a survey , 2007, International Journal of Document Analysis and Recognition (IJDAR).

[5]  Peter Kulchyski.  and , 2015 .

[6]  Umapada Pal,et al.  Handwriting segmentation of unconstrained Oriya text , 2006 .

[7]  K Mahesh Babu,et al.  Vehicle number plate detection and recognition using bounding box method , 2016, 2016 International Conference on Advanced Communication Control and Computing Technologies (ICACCCT).

[8]  G CaseyRichard,et al.  A Survey of Methods and Strategies in Character Segmentation , 1996 .

[9]  Alireza Alaei,et al.  A new scheme for unconstrained handwritten text-line segmentation , 2011, Pattern Recognit..

[10]  Utpal Roy,et al.  A Novel Approach to Skew Detection and Character Segmentation for Handwritten Bangla Words , 2005, Digital Image Computing: Techniques and Applications (DICTA'05).

[11]  Ioannis Pratikakis,et al.  Text line detection in handwritten documents , 2008, Pattern Recognit..

[12]  Made Windu Antara Kesiman,et al.  A New Scheme for Text Line and Character Segmentation from Gray Scale Images of Palm Leaf Manuscript , 2016, 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[13]  Uma Mahadevan,et al.  Gap metrics for word separation in handwritten lines , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[14]  Giovanni Soda,et al.  Artificial neural networks for document analysis and recognition , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Umapada Pal,et al.  Touching numeral segmentation using water reservoir concept , 2003, Pattern Recognit. Lett..

[16]  Li Sun,et al.  Novel character segmentation method for overlapped Chinese handwriting recognition based on LSTM neural networks , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[17]  Eric Lecolinet,et al.  A Survey of Methods and Strategies in Character Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Nobuyuki Otsu,et al.  ATlreshold Selection Method fromGray-Level Histograms , 1979 .

[19]  U. Pal,et al.  Segmentation of Bangla unconstrained handwritten text , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..