Method for making dictionary, hand-written input method and apparatus

Abstract

The invention discloses a method for manufacturing a dictionary, a handwriting input method and equipment. The method for manufacturing the dictionary can predict a character input by strokes so as to relieve the burden of a user. The method comprises the following steps: the feature of the integral character of an integral character sample of characters and the feature of partial strokes of a partial stroke sample of the characters with the number of the strokes larger than a preset value are extracted; and a learning algorithm by a machine is used to carry out learning to the feature of the integral character and the feature of the partial strokes to generate an integral character template and/or a partial stroke template of the characters, which are used as items of the dictionary. The system has the advantages of simple structure, low hardware requirement, rapid identification speed, high identification rate, and so on, and can be realized in an embedded type system and so on.

Description

technical field [0001] The invention relates to character input, in particular to a dictionary making method, a handwriting input method and a device applied to electronic products, which can predict the characters to be input by using the input strokes, so as to reduce the burden of the user. Background technique [0002] For a long time, the fast input of non-alphabetic characters such as Chinese characters has been a difficult problem that plagues people, because the keyboard of a computer is suitable for the input of Western languages ​​​​such as English, but not for the input of Chinese characters. [0003] The input of Chinese characters is usually divided into two types: keyboard input and handwriting input. Keyboard input is to assign a certain code to each Chinese character according to certain coding rules, and to identify Chinese characters through keyboard input codes, such as various pinyin input methods and Wubi font input methods. Handwriting input recognizes...

AI Technical Summary

Problems solved by technology

[0007] However, the prediction steps of the handwriting input method in Patent Document 1 are too complicated, and it uses a total of 68 neural networks involving two types and involves more than 5M parameters, resulting in a very complicated prediction process

Although the method of Patent Document 2 provides a method of predicting the input result through matching without writing complete characters, this invention processes the entire input stroke as an image, resulting in low efficiency

Images