Method and system for inputting visual character based on dynamic track

Abstract

The invention provides a method and a system for inputting a visual character based on a dynamic track. The method comprises the steps of: selecting the class of the character to be input from a character template library, adjusting the state of inputting the visual character; entering the character input state to obtain the dynamic track of inputting the character; adjusting dynamic track data of the obtained character, matching the dynamic track data with the character style in the classified template library, identifying the input character to obtain the identification result; returning to adjust the state of inputting the visual character again, and inputting a new character until inputting is finished. The method has high instantaneity and high accuracy of identifying the character.

Description

technical field [0001] The invention relates to a machine character input method and system, in particular to a dynamic track-based visual character input method and system. Background technique [0002] Machine character visual input technology has been developed for many years, and has been widely used in video surveillance, industrial inspection and other fields, and its application in the entertainment field has gradually increased. Various companies have launched their own visual interactive entertainment products, especially last year. After the kinect, a somatosensory interaction device based on depth sensing technology, human-computer interaction recognition based on machine vision has entered a new stage of rapid development. [0003] Visual interactive recognition technology solves the problem that traditional input devices cannot handle three-dimensional or multi-degree-of-freedom input. However, so far, the field of machine vision still lacks an efficient and na...

AI Technical Summary

Problems solved by technology

One method is to generate semantic commands by obtaining information about the spatial form of hands or markers and analyzing them, but this method has high system complexity, and the distinguishable semantics are particularly limited, so it is not suitable for applications; One method is to use an ordinary camera to construct a virtual keyboard to realize input. Although it is less complex than the previous input device, it still does not get rid of the limitation of the conventional "keyboard". The accuracy of the system in character input is not high, and it is easy to generate Misoperation, unable to realize natural and continuous visual character input function

Images