Character recognition method and apparatus

Abstract

The invention relates to a character recognition method and apparatus. The method comprises: obtaining an input text image; performing text line segmentation on the text image to obtain a text line region of the text image; performing character region segmentation on the text line region according to text character attributes to obtain character region information; and according to the character region information, performing single character segmentation in combination with the text image to obtain a character segmentation result. According to the character recognition method and apparatus, the text segmentation can be accurately performed, so that the recognition performance of OCR (Optical Character Recognition) is greatly improved; and the scheme has relatively high practical values in various text recognition applications.

Description

technical field [0001] The invention relates to the technical field of character recognition, in particular to a character recognition method and device. Background technique [0002] OCR (Optical Character Recognition, Optical Character Recognition) means that electronic devices (such as scanners or digital cameras) check characters printed on paper, determine their shapes by detecting dark and bright patterns, and then use character recognition methods to translate the shapes into computer text. Process; that is, the process of scanning text data, analyzing and processing image files, and obtaining text and layout information. [0003] Among them, when performing character recognition, image and character segmentation is usually required. Among them, image segmentation refers to dividing the image into several non-overlapping regions according to features such as gray scale, color, texture and shape, and making these features show similarities in the same region, but show...

AI Technical Summary

Problems solved by technology

[0006] 1. For images with uneven illumination, the segmentation effect of existing algorithms is often very poor;

[0007] 2. The segmentation of the text area is incomplete, often showing that a single character is divided into multiple blocks, or multiple characters cannot be separated, etc., which makes recognition difficult for OCR;

[0008] 3. There are too many noise areas, that is, many of the segmented character areas do not actually contain characters

Images