The first step in the text recognition process is represented by the text line segmentation procedures. Only after text lines are correctly identified can the process proceed to the recognition of individual characters. This paper proposes a line segmentation algorithm based on the computation of an information content level, called energy, for each pixel of the image and using it to execute the seam carving procedure. The algorithm proposes the identification of text lines which follow the text more accurately with the expected downside of the computational overhead.