Comparative Study of Text Line Segmentation Algorithms on Low Quality Documents

Segmentation of text lines is one of the important steps in the Optical Character Recognition system. Text Line Segmentation is pre-processing step of word and cha ra ter segmentation. Text Line Segmentation can be viewed simple for printing documents which contains distinct spaces between th e lines. And it is more complex for the documents w here text lines are overlap, touch, curvilinear and variation of space between t ext lines like in Telugu scripts and skewed documen ts. The main objective of this project is to investigate different text line segme ntation algorithms like Projection Profiles, Run le gth smearing and Adaptive Run length smearing on low quality documents. These met hods are experimented and compare their accuracy an d results.