Handwriting track detection, standardization and online-identification and abnormal radical collection

Abstract

The invention relates to a method and a device for handwriting track detection, a method and a device for handwriting track standardization, a method and a device for handwriting track online-identification, and a method and a device for abnormal radical collection. According to one embodiment of the invention, the method for detecting the character handwriting track is provided. The method comprises the following steps: first judgment is made on each stroke of a handwriting track according to the geometric features of the stroke based on predetermined abnormal radicals to judge whether the stroke is an abnormal radical; and if the stroke is not an abnormal radical, second judgment is made to judge whether the stroke is part of an abnormal radical and whether the combination of the stroke and an adjacent stroke is an abnormal radical, wherein the second judgment is performed on the basis of the geometric features of the stroke and the geometric features of the adjacent stroke.

Description

technical field [0001] The present disclosure relates to methods and devices for detection, normalization, and online recognition of handwriting traces of characters, and methods and devices for collecting abnormal radicals. Background technique [0002] Character systems represented by Chinese and Japanese kanji (also known as square characters or ideographic characters) usually contain multiple strokes, some of which are often used as radicals (radical) (such as, but not limited to, radicals in Chinese). In addition, certain radicals can form higher-level radicals with, for example, adjacent strokes. [0003] The writing of characters such as pictographs is usually much more complicated than the phonetic character system represented by English. For example, Chinese (Chinese characters) has a standard writing style for each character, including: the number of strokes, the writing order (stroke order) and direction of the strokes, and so on. [0004] For the character sys...

AI Technical Summary

Problems solved by technology

However, due to the deformation of the stroke shape, the recognition accuracy of the best candidate (e.g., the first best candidate) for offline recognition is usually not as high as that for online recognition.

And in order to be robust to the deformation of stroke shape, offline recognition requires much higher processing power and memory cost, otherwise it is difficult to achieve the same accuracy as online recognition

Images