会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 9. 发明申请
    • COMMUNICATION METHOD AND APPARATUS FOR USER TERMINAL
    • 用户终端的通信方法和设备
    • US20090144779A1
    • 2009-06-04
    • US12325363
    • 2008-12-01
    • Bin WanYanglin ZhouZhongliang Miao
    • Bin WanYanglin ZhouZhongliang Miao
    • H04N7/16H04M1/00
    • H04L67/303H04L65/1069H04L69/24H04L69/40H04W76/10
    • A communication method and apparatus for a user terminal provided in the present invention can detect the user terminal, obtain first capability information on a video communication of a wireless network, and second capability information on the video communication of said user terminal, process the first capability information and the second capability information to generate video communication capability indication information, and select one of operations to perform according to said video communication capability indication information, said operations including enabling a video session or enabling the video session after closing at least a part of applications being used by said user terminal or enabling an audio session. Such a processing scheme of the communication for a user terminal is of high efficiency, with a clear process and can be easily optimized, with an improved success rate for establishing a video session at a time.
    • 本发明提供的用户终端的通信方法和装置可以检测用户终端,获取无线网络的视频通信的第一能力信息,以及关于所述用户终端的视频通信的第二能力信息,处理第一能力 信息和第二能力信息,以产生视频通信能力指示信息,并且根据所述视频通信能力指示信息选择要执行的一个操作,所述操作包括在关闭至少一部分应用之后启用视频会话或启用视频会话 由所述用户终端使用或启用音频会话。 这种用于用户终端的通信的处理方案具有高效率,具有清晰的处理并且可以容易地优化,同时具有用于一次建立视频会话的成功率提高。
    • 10. 发明申请
    • Signature verification
    • 签名验证
    • US20070154071A1
    • 2007-07-05
    • US11321232
    • 2005-12-29
    • Zhouchen LinLiang WanBin Wan
    • Zhouchen LinLiang WanBin Wan
    • G06K9/00
    • G06K9/00181
    • Methods and systems for training a computer to recognize and verify an individual's signature are provided. One illustrative method extracts a plurality of both global and local features from a relatively small sample of handwriting samples. In one such embodiment, only 5 samples are needed from an individual without requiring forgeries. In yet another embodiment, only three global parameters are utilized, thus reducing the complexity, and processing power, of the system. Utilizing such few global parameters also facilitates fine tuning of the systems. Further aspects of the invention relate to a multi-stage statistical system for on-line signature verification. In one embodiment, the system may comprise a simplified GMM model built on global signature properties and a left-to-right HMM model based on segmental features. In one embodiment, specific strategies are utilized to create model simplification and initialization in contrast to general GMM and HMM models.
    • 提供了用于训练计算机以识别和验证个人签名的方法和系统。 一个说明性方法从相对较小的笔迹样本样本中提取多个全局和局部特征。 在一个这样的实施例中,仅需要5个样本,而不需要伪造。 在另一个实施例中,仅使用三个全局参数,从而降低系统的复杂性和处理能力。 利用这么少的全局参数也有助于系统的微调。 本发明的其它方面涉及用于在线签名验证的多阶段统计系统。 在一个实施例中,系统可以包括基于全局签名特性的简化GMM模型和基于段特征的从左到右HMM模型。 在一个实施例中,与通用GMM和HMM模型相反,具体策略被用于创建模型简化和初始化。