A line-based representation for matching words in historical manuscripts

In this study, we propose a new method for retrieving and recognizing words in historical documents. We represent word images with a set of line segments. Then we provide a criterion for word matching based on matching the lines. We carry out experiments on a benchmark dataset consisting of manuscripts by George Washington, as well as on Ottoman manuscripts.

Research highlights
► Efficient and effective recognition of English and Ottoman word images.
► Efficient and effective retrieval of English and Ottoman word images.
► An effective and efficient representation of word images based on line descriptors.
► A new word-matching criterion using pairs of matched line descriptors.