基于Face++的手势识别系统设计与实现

Design and Implementation of Gesture Recognition System Based on Face

鉴于Face++在人脸检测与识别领域的巨大成功,针对目前手势识别应用研究偏少的情况,本文将Face++人体识别中的手势识别方法加以应用,设计并实现了基于Face++的手势识别系统。该系统首先利用手势样本库图片或者摄像机实时采集的手势图片作为待识别样本,接着将样本作为一个参数,通过Post调用方法调用Face++指定的URL接口,最后解析通过接口调用返回的Json串并使用Open CV库函数将识别结果显示给用户。实验结果表明,使用Face++手势识别方法识别静态手势,系统具有识别率高、实时性好、鲁棒性佳的优点。

Considering the great success of Face++in the field of face detection and recognition,in view of the current lack of research on gesture recognition applications,this paper applies the gesture recognition method in Face++human body recognition,and then designs and implements the gesture recognition system based on Face++.Firstly,the system uses the gesture pictures which from sample library or been captured by the camera in real time as the samples to be identified;Secondly,the system takes one of the sample as a parameter,calls the URL interface which is specified by Face++through the Post calling method;Finally,the system parses the Json string which is returned by the interface called and then uses OpenCV functions to display the recognition result to the users.The experimental results show that using Face++gesture recognition method to identify static gestures,the system has the advantages of high recognition rate,good real-time performance and good robustness.