A Text Image Vectorization Method and System Based on Skeleton Guidance

Abstract

The invention relates to a character image vectorization method and system based on framework instruction. The steps of the method include: 1) with respect to a single character image, the system uses morphology and an anisotropic diffusion algorithm to perform preprocessing including stroke connection and edge smoothing on the image; 2) obtaining a framework of the character image and key points on the framework; 3) extracting an edge contour of the character image and classifying curvature extreme points of the edge contour of the character image into angular points and connection points; 4) using a weighted dynamic planning algorithm to delete redundant connection points; 5) performing curve fitting and enabling curvatures at the connection points to be continuous. Compared with the prior art, the vectorization method and system are capable of maintaining important details in a character writing style and also capable of deleting noises on stroke contours at the same time; and manual intervention is completely not needed and the algorithm is capable of automatic operation so that vectorized batch operation is facilitated.

Description

technical field [0001] The present invention relates to an image vectorization method and system, in particular to a method for image denoising, image enhancement, image skeleton generation, edge detection and curve fitting, and a text image vectorization method and system based on skeleton guidance, belonging to computer Image processing technology field. Background technique [0002] Calligraphy is a precious cultural treasure in the 5,000-year history of civilization in China. It is known as: poetry without words, dance without lines, paintings without pictures, and music without sound. From oracle bone inscriptions and bronze inscriptions to big seal script, small seal script, and official script, to cursive script, regular script, and running script of the Eastern Han, Wei, and Jin Dynasties, calligraphy has always exuded a unique artistic charm. [0003] Chinese calligraphy has a long history, the style of calligraphy has evolved and changed, and the art of calligraph...

AI Technical Summary

Problems solved by technology

[0005] When traditional commercial companies vectorize calligraphy text images, in order to make the effect of vectorization better, they often add some manual intervention and guidance, which increases the cost of vectorization and slows down the speed of vectorization

[0006] In the existing automatic vectorization methods and systems, the same processing algorithm is used for all input images, the image content is never analyzed, and the characteristics of the image itself are not paid attention to, which makes it difficult for these methods to distinguish the noise in the image And detail features, if all the noise is removed, the details of the image will be lost at the same time; if too many details are retained, the noise will make the result look very ugly and lose the meaning of vectorization

Images