For the last few decades several researches have been conducted on Online handwriting analysis. But scholars have unanimously agreed to the fact that it is challenging research area. To recognize with perfect prediction some pre-processing steps are essential. In this paper an honest endeavor is made to present dehooking as one of the important pre-processing steps. Here Bengali online handwritten Characters and words are considered as samples for removing hooks. Hooks are basically common artifacts used by people during fast writing. Hooks are very common issues present at the beginning in very rare case and the end of character stroke in maximum case and are generated by the pen-down and pen up movements respectively. Dehooking is the process of eliminating such unwanted strokes that appear due to inaccuracies in pen down position. Dehooking algorithms are applied to remove hooks. Here, strokes are detected by comparing the number of points with a threshold value. If the value is greater than the threshold value, the mark is retained or it is removed otherwise. In this new and innovative approach we focus on the dehooking at the end of character stroke and consider last 20 percent of each stroke for checking, according to distance from the co-ordinate of the first pixel. In last 20 percent of a stroke, we calculated angle among three consecutive pixels. If in a particular point, angle among three consecutive pixels is falling suddenly then immediately we pointed out that point. After pointing out the angle falling place we checked the entire remaining pixel after that point, whether all the remaining points are getting fade slowly or not. If it is found that all the remaining points are getting faded slowly then it can be assumed that it is a hook. After detecting the hook of a particular stroke we remove all the remaining pixels from the falling angle place so that hook can be removed and the handwritten character remains hook less. I have tested 4000 Bengali online handwritten characters and have got 97.02 percent of accuracy.

Online, Handwriting, Character, Angle, Fade, Hook

[1] Mazumdar, Bijaychandra,“The history of the Bengali language” (Repr. [d. Ausg.] Calcutta, 1920. ed.). New Delhi: Asian Educational Services. p. 57. ISBN 8120614526, 2000.
[2] Aini Najwa Azmi, Dewi Nasien, Siti Mariyam Shamsuddin,“A review on handwritten character and numeral recognition for Roman, Arabic, Chinese and Indian scripts”, International Journal of advanced studies in Computer Science and Engineering, Vol 2 issue 4, 2013
[3] Fareeha Anwar, Muhammad Adnan Aftab, Dr.Syed Afaq Hussain, Dr.Ayyaz Hussain “Preprocessing of Online Urdu Handwriting for Mobile Devices”, International Journal of Computer Science and Network Security, Vol.17 No.10, October 2017
[4] Anitha Mary M.O. Chacko, Dhanya P.M.,“Handwritten Character Recognition in Malayalam Scripts– a Review”, International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 1, January 2014
[5] Muhammad Imran Razzak, Syed Afaq Hussain, Muhammad Sher, Zeeshan Shafi Khan, “Combining Offline and Online Preprocessing for Online Urdu Character Recognition”, Proceedings of the International Multi Conference of Engineers and Computer Scientists 2009, Vol I IMECS 2009, March 18 - 20, 2009, Hong Kong