DSpace Repository

Segmentation and Alignment of Multi-oriented and Curved Text Lines from Document Images

Show simple item record

dc.contributor.author Too, Boaz K.
dc.contributor.author Prabhakar, C. J.
dc.date.accessioned 2018-07-10T07:32:45Z
dc.date.available 2018-07-10T07:32:45Z
dc.date.issued 2015-06
dc.identifier.citation International journal of Machine Intelligence, (Bioinfo Publications), vol. 6, issue 1, pages 426-434 en_US
dc.identifier.issn 0975-9166
dc.identifier.uri http://hdl.handle.net/123456789/1754
dc.description.abstract In this paper, we present a novel approach to segment and align multi-oriented and curved text-lines from document images. We assumed that the input document image contains text-lines with arbitrary orientation and identified the arbitrary text string based on projection profile. We employed anisotropic Gaussian filter bank on the identified arbitrary text region in order to smooth the text region, which helps to detect the ridges which is a representative of a text-line path. The ridges are then labeled and a cubic B-spline is fitted to the text-line path points. The orientation and curvature features of the text-line path is estimated using orientated gradients for each point and corresponding curvature to these text-line path are computed. Text is aligned along the horizontally transformed line by rotating individual characters based on the computed curvature information. Finally, the aligned text-lines are extracted, which can be fed into OCR for recognition. The evaluation metrics was evaluated at text-line segmentation level and the results posted show a significant improvement. The resulting system is proven to provide better results than most state of the art algorithms en_US
dc.language.iso en en_US
dc.subject Text-Lines detection en_US
dc.subject Text-line segmentation en_US
dc.subject oriented gradients en_US
dc.title Segmentation and Alignment of Multi-oriented and Curved Text Lines from Document Images en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Browse

My Account