Method and device for acquiring character image skeleton feature descriptor

Abstract

The invention provides a method and a device for acquiring a character image skeleton feature descriptor. The method comprises the steps of S1, performing color block segmentation on an input image, obtaining horizontal and vertical color segment lines and endpoints thereof of a color block connected domain, and obtaining midpoints of the horizontal and vertical color segment lines; s2, judging the midpoints of the horizontal color segment line and the vertical color segment line, finding out skeleton points, dividing the types of the skeleton points, and obtaining a corrected skeleton line; s3, finding out the longest horizontal line segment and the longest vertical line segment from the skeleton lines after position correction, and carrying out the dividing and coding of the stroke linesof the skeleton line segments; and S4, sorting the stroke linear codes of the skeleton line segments according to a preset sequence, and taking a set of the sorted stroke linear codes of the skeletonline segments as a character image skeleton feature descriptor. The device comprises a first acquisition module, a second acquisition module, a processing module and a generation module. According tothe method and the device, the stroke extraction accuracy of the character can be improved, and the matching effect of the same or similar images in character image recognition retrieval is improved.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method and device for acquiring character image skeleton feature descriptors. Background technique [0002] Image skeleton is a simplified description of object shape features, and it is of great significance to correctly obtain image skeleton features in the application of image recognition technology. A concise and accurate image skeleton can highlight the overall structure of the object described in the image and reflect the shape and composition information of the object, so it plays an important role in digital image analysis. Image skeleton extraction is an important means for image recognition and line image target analysis . [0003] The recognition of text images is mainly to obtain the text content in the image through recognition, and the most commonly used method is OCR text image recognition. [0004] Although OCR text image recognition can recognize text informa...

AI Technical Summary

Problems solved by technology

[0006] 1) The strokes of the skeleton line of the text image extracted by the traditional method do not correspond to the strokes of the text itself, and the skeleton lines of horizontal and vertical strokes often have "twigs" line segments, resulting in distortion of the skeleton line;

[0007] 2) There are differences in the skeleton lines extracted from different fonts of the same text, so that the image skeleton features of the same text are different, which makes it difficult to match the image skeleton features when retrieving images of the same text

Images