首页> 外国专利> RCE-NNRestricted Coulomb Energy Neural Network Method for recognizing hand gesture based on RCE-NN

RCE-NNRestricted Coulomb Energy Neural Network Method for recognizing hand gesture based on RCE-NN

机译:基于RCE-Nn的识别手势的RCE-NnRestricted Couromb能量神经网络方法

摘要

A method for recognizing a hand gesture according to an embodiment of the present invention includes the steps of, by a gesture collecting device, generating gesture data as a user performs a gesture and providing it to a server; performing pre-processing on the gesture data received from the gesture collecting device to generate a list, the server inputs the generated feature vector into a doubly formed Restricted Coulomb Energy Neural Network (RCE-NN) algorithm, It may be performed including an AI calculation step of classifying one gesture data by class in a manner that calculates dissimilarity and classifies the calculated dissimilarity value into a class having a minimum value.
机译:用于识别根据本发明的实施例的手势的方法包括通过手势收集设备的步骤,以便作为用户生成手势数据执行手势并将其提供给服务器; 对从手势收集设备接收的手势数据执行预处理以生成列表,服务器将生成的特征向量输入到双重形成的受限库仑能量神经网络(RCE-NN)算法中,可以执行包括AI计算 按类分类一个手势数据的步骤以计算不相似性并将计算的不相似值分类为具有最小值的类。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号