期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2013
卷号：10
期号：5
出版社：IJCSI Press
摘要：In Indian scenario, most of the time the office documents such as forwarded notices and other documents are multilingual with multiple skews. This poses new challenges in the field of document image analysis. In this direction we are presenting a method of estimating the skew in handwritten multilingual documents. From a handwritten multilingual document image each word is segmented using morphological operations and connected component analysis. Skew of each word is estimated by fitting a minimum circumscribing ellipse. The orientation of each word is estimated and then words are clustered using adaptive k-means clustering to identify the multiple blocks present in the document and average orientation of each block is estimated. In order to corroborate the efficacy of the proposed model experimentation on our own dataset is carried out.
