Method and device for pre-processing block Arab characters

Abstract

The invention discloses a method and a device for pre-processing block Arab characters, belonging to the field of optical character recognition. The method comprises the following steps of: step 1, performing a gravity centre analysis on the character images obtained after a segmentation, and calculating the deviation degrees of the gravity centres of the character images; if the deviation degrees of the gravity centres of the character images are less than an appointed threshold, then turning to step 3; or else, turning to step 2; step 2, adjusting a confidence frame according to the obtained deviation degrees of the gravity centres, and determining the character images in the confidence frame; and step 3, loading the character images in the confidence frame on a recognition core to recognize. In the invention, a confidence frame is selected via a gravity centre analysis before a character recognition is performed, and the character images are adjusted by the confidence frame, then the character images at the gravity centre parts in the confidence frame are recognized, so that the character images cannot be influenced by an improper selection for segmentation points while segmenting characters, thereby avoiding the influence of elongation characters in Arabic and improving the recognition effect of the character recognition.

Description

[0001] technical field [0002] The invention belongs to the field of optical character recognition, and relates to a character preprocessing method and device, in particular to a printed Arabic character preprocessing method and device. [0003] Background technique [0004] In character recognition, it is necessary to locate the character image from the original image, and then perform single character recognition based on the positioned coordinates. In printed Arabic, words are joined together at the baseline, and the length of the elongated character in some words in the line is often longer in typesetting to keep the text in each line intact. Such as figure 1 As shown, if a character has a long elongated character, but the shape of the character inevitably has a certain deformation, which makes the character difficult to recognize, the existing method generally first breaks the elongated character by segmentation Open, and then identify the obtained segmentation bloc...

AI Technical Summary

Problems solved by technology

like figure 1 As shown, if a character has a long elongated character, but the shape of the character inevitably has a certain deformation, which makes the character difficult to recognize, the existing method generally first breaks the elongated character by segmentation Open, and then identify the obtained segmentation blocks separately, but the segmentation point adopted during segmentation will affect the recognition effect, and when the segmentation point selection is not very accurate, the stretching between Arabic characters Characters will inevitably affect the recognition of characters

Images