Horizontal and vertical line detection and removal for document images

Abstract

The invention relates to horizontal and vertical line detection and removal for document images and provides a method of removing horizontal and vertical lines from a document. The horizontal line removal method includes: for a column of black pixels at each horizontal position along the line, removing them if their maximum stroke width is less than the median value of maximum stroke widths in a small window centered at that horizontal position; Remove connected components remaining in the horizontal line bounding box that do not extend significantly above or below the bounding box boundaries; and Perform closing operation to join broken pieces of character strokes caused by underline removal. This method preserves character strokes while removing underlines. The vertical line removal method includes: for vertical lines that have large height to width ratio, remove parts of such lines that are not at intersection of with horizontal or near-horizontal lines; remove all remaining connected components that touch neither left nor right boundary of the bounding box.

Description

technical field [0001] The present invention relates to document image processing, in particular, the present invention relates to methods for detecting and removing horizontal and vertical lines in document images. Background technique [0002] Document images generally refer to digital images representing pages of documents containing large amounts of text. Document images often contain lines, specifically, horizontal and vertical lines, such as table lines, underlining of text, and the like. Because characters (letters and other symbols) are often the focus of document image analysis (such as optical character recognition (OCR), document authentication, etc.), it is often desirable to remove lines. These lines are generally very long in one direction, and if these lines are not explicitly removed, errors and errors may be caused in the connected component analysis performed later. Various methods have been proposed for line detection and removal, such as Hough transform...

AI Technical Summary

Problems solved by technology

However, when these methods are applied to real documents, they are usually affected by the image quality and the degree of binarization of the image

Furthermore, in known line removal methods, the removal of a text underline may often change the character of the character crossed by the underline

Many known methods also suffer from incomplete line removal

Images