Self-adaptive hand-written discrimination system and method

Abstract

This invention provides an adaptive handwriting recognition system and method. The adaptive handwriting recognition system comprises: handwrite character input module, allowing users to input characters, and create eigenvector corresponding with the characters; universal character characteristic template library, used to store character collection obtained through samples training beforehand and their counterparts the characteristics template; user character characteristic template library, for storing users handwriting characteristics template; input character recognition module, based on the above eigenvector and universal character characteristic template in universal character characteristic template library, identify the input characters, update user character characteristic template library according to recognition results. Therefore, according to the system and method by this invention, not only can improve the accuracy of handwriting recognition, but also can adapt to different users handwriting characteristics.

Description

technical field [0001] The invention relates to a handwriting recognition system and method, in particular to an adaptive handwriting recognition system and method capable of automatically adapting to the characteristics of handwritten characters of different users. Background technique [0002] The use of digital devices to input handwritten characters has become a very common phenomenon. These digital devices usually refer to devices such as Tablet-PCs, PDAs and handwriting mobile phones with touch screens and other sensors. The corresponding handwriting recognition technology is widely used. use. [0003] In the current relatively mature and commercial handwriting recognition systems, the character feature templates used for character recognition are basically trained through a large number of training samples. Different people may write the same character in many different ways. Through A large number of samples written by different people are trained with the training ...

AI Technical Summary

Problems solved by technology

This method depends on whether the selection of multiple classifiers is suitable. Even if the selected classifier is relatively accurate, the complexity of the algorithm will continue to increase for different writing methods of different users, and the corresponding storage space consumption will continue to increase. , the resulting improvement in handwriting recognition accuracy is still limited

[0005] In addition, the characteristics of the user's handwriting will change with the user's age or body muscles and other conditions. If the above method is used, the user needs to re-register or adjust the classifier. From this point of view, the existing methods cannot Well suited for individual user use

Images