Text Line Segmentation with the Parametric Water Flow Algorithm

Abstract

The manuscript proposes an extension to the water flow algorithm for the text line segmentation. The basic algorithm assumes the hypothetical water that flows under few specified angles of the document image frame from left to right and vice versa. It establishes wetted and unwetted image regions. The unwetted regions are labeled and separated. They are of the major importance for the text line segmentation. The extension of the algorithm means modification of water flow function, which creates the unwetted region. Hence, the linear water flow function used in the algorithm is changed with its power function counterpart. Extended method is tested, examined and evaluated under different text samples. Results are encouraging due to improved text line segmentation.

DOI: http://dx.doi.org/10.5755/j01.itc.45.1.11197