Text information recognition method and device

Abstract

The present invention proposes a text information recognition method and device, wherein the text information recognition method includes: receiving text information input by a user, and obtaining corresponding elements from the text information; generating a recognition result set based on the elements; and The recognition results in the recognition result set are processed based on a preset algorithm to output target recognition results. In the text information recognition method and device of the embodiment of the present invention, the stroke pre-segmenter accurately performs stroke segmentation on the text information input by the user to obtain the corresponding elements, and generates a recognition result set according to the similarity, and according to the preset language model Construct the Markov chain, and obtain the information corresponding to the path with the highest generation probability as the target recognition result. When the user input text information in the handwriting area without restriction, the text information input by the user can be accurately recognized, effectively improving the recognition accuracy.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a text information recognition method and device. Background technique [0002] Handwriting recognition refers to the process of converting the orderly trajectory information generated during handwriting input into text information, that is, a mapping process from the coordinate sequence of handwriting trajectory to text information, which is one of the most natural and convenient means of human-computer interaction. With the popularization of intelligent tools such as smart phones and tablet computers, the application of handwriting recognition technology is becoming more and more extensive. [0003] At present, many input method application software support the handwriting input method, and the user can input stroke sequences by handwriting, and the application software can recognize the stroke sequence as text information, thereby realizing text input. [0004] However, if ...

AI Technical Summary

Problems solved by technology

[0004] However, if the user inputs multiple characters at once, and the input method is not the normal left-to-right input method, but an abnormal input method such as bottom-to-top, the recognition rate of the text information will be reduced

Images