Search International and National Patent Collections

1. (WO2018145316) MOUSE GESTURE RECOGNITION METHOD AND APPARATUS

Pub. No.:    WO/2018/145316    International Application No.:    PCT/CN2017/073382
Publication Date: Fri Aug 17 01:59:59 CEST 2018 International Filing Date: Tue Feb 14 00:59:59 CET 2017
IPC: G06F 3/01
Applicants: SHENZHEN HUADEE TECHNOLOGIES CO.,LTD.
深圳市华第时代科技有限公司
Inventors: ZHANG, Xiaomin
张小敏
LUO, Jian
罗健
HAN, Ronghua
韩荣华
TANG, Chanjuan
唐婵娟
Title: MOUSE GESTURE RECOGNITION METHOD AND APPARATUS
Abstract:
Disclosed in the present invention is a mouse gesture recognition method. The method comprises: detecting a mouse gesture inputted by a user by means of a mouse operation, and obtaining a mouse gesture image to obtain an image to be recognized; preprocessing the image to be recognized, so as to obtain a feature vector of the image to be recognized; and inputting the feature vector into a pre-trained BP neural network, so as to obtain a recognized character. The present invention also provides a mouse gesture recognition apparatus. In the mouse gesture recognition method and apparatus provided in the present invention, by using artificial intelligence of a BP neural network, a feature vector of a preprocessed mouse gesture image is inputted into a trained BP neural network, and accordingly, the recognition result can be obtained. Accordingly, due to the advantages of the BP neural network, such as distributed information storage, information parallel processing, information self-organizing and self-learning, mouse information inputted by a user can be processed in time, a great deal of training ensures the recognition precision; in addition, the mouse gesture recognition method and apparatus can be also applied in various types of application programs, thereby greatly improving user experience.