Method for extracting strokes of handwritten Chinese characters

Abstract

The invention discloses a method for extracting strokes of handwritten Chinese characters. The method comprises the following steps of: preprocessing a character image; calculating direction point angle features of the pixels; calculating direction point angle features of the inflection point group; and stroke extraction based on the stroke skeleton and the contour. According to the method, off-line handwritten Chinese characters can be converted into corresponding strokes, then downstream tasks such as Chinese character handwriting recognition and writer identity recognition are carried out based on the strokes, and the interpretability of the whole processing flow can be greatly improved. By using the method provided by the invention, off-line handwritten Chinese characters can be more accurately converted into corresponding strokes, so that the accuracy of downstream tasks such as subsequent Chinese character handwriting recognition and writer identity recognition is improved.

Description

technical field [0001] The invention relates to word processing technology, in particular to a method for extracting strokes of Chinese handwritten characters. Background technique [0002] The invention of characters is an important driving force for the development of human civilization. After entering the information age, how to process characters has always been the focus of research in related disciplines, such as the recognition of various online / offline handwritten characters, authentication based on writing style, Automatic processing of various documents, intelligent education, etc., especially with the rapid development of deep learning technology, various word processing technologies have been widely used. However, in the above process, due to the black-box characteristics of the deep neural network, the interpretability of the final model is not strong, and it is difficult to associate it with the existing knowledge intuitively, which is not conducive to the furt...

AI Technical Summary

Problems solved by technology

In the above process, the key problems that need to be solved are: the processing of strokes with different widths, the hairline and bifurcation of the skeleton, the deformation of strokes, etc.

However, when dealing with general handwritten text, due to problems such as continuous writing and writing deformation, the error of stroke extraction is relatively large, which seriously affects the performance of downstream tasks.

There are two reasons for this. One is that most of the existing technologies only use one of the outline or skeleton information, and there is no comprehensive utilization of the high-level information of these two types of characters; Effectively describe the expression, resulting in the underutilization of the character structure features contained in it

Images