Underlined text image preprocessing method and device

Abstract

The invention discloses an underlined text image preprocessing method and device, relating to the field of optical character recognition. The method comprises the following steps: acquiring the position of each text line in a text image; for the position of each text line, searching each text line based on a run-length search method; if the preliminary determination result shows that an underline exists in the text line, locating the position of the initial upper boundary of the underline; by using the initial upper boundary of the underline as an initial pixel line, locating the underline region based on run-length search and connected domain analysis methods; separating out stroke regions of characters from the underline region, thus obtaining a region to be deleted; and setting the foreground information in the region to be deleted into the background, thus obtaining a character region having no underline. By searching each text line based on the run-length search method for the position of each text line, the invention solves the problem that a text having an underline (especially an underline conglutinated with characters) is difficult to recognize, improves the character recognition rate, and enhances the adaptability of the recognition core.

Description

technical field [0001] The invention belongs to the field of optical character recognition (OCR), and relates to an underlined text image preprocessing method and device. Background technique [0002] In printed character recognition, the general processing flow is: first divide the text image into several lines, so that each text line contains only a single line of text; and then further character segmentation and recognition. [0003] If there is an underscore under the character, it will not only affect the normal segmentation of the character, but also cause the character recognition engine to fail to recognize the corresponding character correctly. Therefore, it is usually necessary to remove the underscore below the character before character segmentation and recognition. [0004] In the prior art, a simple straight line detection method (such as Hough transform, etc.) is usually used. If a long straight line is detected under the character image, the image in the lin...

AI Technical Summary

Problems solved by technology

[0005] This method is effective for the underline separated from the character, but for the case where the character and the underline are glued together, the straight line may not be correctly positioned, or the glued part of the character and the underline may be deleted, which will affect the correct recognition of the character and reduce the recognition rate of the character and identify core fitness

Images