期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2018
卷号：7
期号：2
页码：155-159
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Handwriting recognition has been one of the most interesting research areas for last few years. Many scholars have conducted several researches on offline handwriting recognition but online handwriting is still an open space for innovative research. Though it is true that various research works have been done for online handwritten character recognition of English as well as different Indian scripts, online word recognition of Indian script especially Bengali script / words is an on-going research area. Online handwritten word recognition system consists of many pre-processing steps, out of which skew detection and correction is the most important pre-processing step. Only few techniques have been implemented for skew detection and correction of handwritten words. Those already implemented techniques do not give perfect output and has very high time complexity. In this paper an endeavor is made to introduce an unprecedented and innovative approach of skew detection and correction for online Bengali handwritten words. Here the handwritten word is rotated from -45 degree to + 45 degree to calculate the height of the whole word for each degree of rotation and we consider that particular angle where the height of the word is minimum. If it is observed that the height is minimum and same or almost same (± 1) for more than one angle then the width of the word is calculated and the particular angle, where the width is maximum, will be considered. Then the repetition of the stated steps will be done in the busy zone so that the handwritten words can be skew corrected. 3364 Bengali handwritten words from people of different backgrounds have been tested and have got an outstanding result of 97.05% accuracy.
