Method for correcting text image

Abstract

The invention discloses a method for correcting a text image and belongs to the field of optical character recognition. The method comprises the following steps of: positioning a character zone in the text image and extracting suspected characters; recognizing the suspected characters, wherein if the recognition reliability is higher than the reliability reference value of a single character, the effective direction of the characters is positive, otherwise, the suspected characters are rotated counterclockwise respectively for judging the effective direction; extracting and sending the characters having the effective direction to an effective character set; extracting the corresponding text direction until the accumulated value of the recognition reliability in a certain direction is higher than the predetermined recognition reliability; correcting the direction of the image and recognizing and outputting the text image. The method effectively eliminates the influence from unreliable characters, prevents the unreliable zone in the character zone from influencing the judgment of the character direction, is well suitable for the text images having complexity or noise or poor quality and can judge the direction of a text image fast and correctly so as to effectively recognize the text image.

Description

technical field [0001] The invention belongs to the field of optical character recognition (OCR), and relates to a text image correction method. Background technique [0002] When the document to be recognized is converted into a text image by an image recording device (such as a scanner, camera, etc.), the direction of the text is not necessarily positive, and may be rotated by 90°, 180°, or 270°. If the non-positive text image is directly sent to the recognition engine for recognition, the correct recognition result cannot be obtained. [0003] In order to ensure that the information in the text image can be correctly identified and saved as an electronic document, two solutions are usually adopted at present. [0004] Solution 1: Manually correct the image orientation. This method is time-consuming and labor-intensive, especially when operating on a large number of images, the efficiency is extremely low. [0005] Solution 2: Use the identification information in the s...

AI Technical Summary

Problems solved by technology

However, since there is no effective screening of the characters in the area to be recognized, if the selected area contains non-text areas (for example: icons, noise, etc.) or areas with low recognition reliability (for example: poor image quality character), it may cause the average recognition reliability of this area to be lower than the refer

Images