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
    • 26. 发明申请
    • FACE RECOGNITION SYSTEM AND METHOD BASED ON ADAPTIVE LEARNING
    • 基于自适应学习的面部识别系统和方法
    • US20080273766A1
    • 2008-11-06
    • US12115250
    • 2008-05-05
    • Hyun-Soo KimJe-Han YoonHyun-Sik ShimYoung-Hee ParkDo-Hyung KimWoo-Han Yun
    • Hyun-Soo KimJe-Han YoonHyun-Sik ShimYoung-Hee ParkDo-Hyung KimWoo-Han Yun
    • G06K9/00
    • G06K9/00295
    • A face recognition system based on adaptive learning includes a specific person detection and tracking unit for detecting and tracking a specific person from a moving image. A facial feature extraction unit extracts a plurality of facial feature vectors from the detected and tracked specific person. A face recognition unit searches for a given registration model by comparing the extracted facial feature vectors with facial feature vectors of the registration models previously stored in a user registration model database. A learning target selection unit selects a facial feature vector to be added to a record of the given registration model from among the extracted facial feature vectors. A registration model learning unit adds and updates the selected facial feature vector to the record of the given registration model.
    • 基于自适应学习的面部识别系统包括用于从运动图像中检测和跟踪特定人物的特定人物检测和跟踪单元。 面部特征提取单元从检测到和跟踪的特定人物中提取多个面部特征向量。 面部识别单元通过将提取的面部特征向量与先前存储在用户登记模型数据库中的登记模型的面部特征向量进行比较来搜索给定的登记模型。 学习目标选择单元从所提取的面部特征向量中选择要添加到给定登记模型的记录的面部特征向量。 注册模型学习单元将所选择的面部特征向量添加并更新到给定注册模型的记录。
    • 28. 发明申请
    • Apparatus and method for processing collision information in graphic system
    • 在图形系统中处理碰撞信息的装置和方法
    • US20070132766A1
    • 2007-06-14
    • US11634030
    • 2006-12-05
    • Do-Hyung KimSeung-Woo NamIn-Ho Lee
    • Do-Hyung KimSeung-Woo NamIn-Ho Lee
    • G06T15/70
    • G06T17/00G06T2210/21Y10S345/958Y10S345/959
    • An apparatus processes collision information in a graphic system, and includes a first storage unit for loading geometry information of primary and secondary object graphics inputted from outside, and outputting the geometry information of the primary object graphics and geometry information of a plurality of secondary object graphics in which a collision detection operation with the primary object graphics is to be performed; a transformer for transforming coordinates of the secondary object graphics to be coincided with a coordinate system that is based on the primary object graphics; a processor for acquiring a collision point, collision presence information, and a collision depth between the primary and the secondary object graphics simultaneously based on the geometry information of the inputted primary object graphics and that of each of the coordinate-transformed secondary object graphics by using a collision detection operation technique determined by the geometry information properties of the primary and the secondary object graphics; a second storage unit for storing the collision information separately, wherein the collision depths before/after update are stored in two areas separately; and an updating unit for updating the collision point and the collision presence information whenever they are newly outputted from the processor, wherein the collision depth is updated based on the result of comparison with the previously stored collision depth.
    • 一种装置处理图形系统中的碰撞信息,并且包括用于加载从外部输入的主要和次要对象图形的几何信息的第一存储单元,并且输出多个次要对象图形的主要对象图形和几何信息的几何信息 其中将执行具有主要对象图形的碰撞检测操作; 用于将辅助对象图形的坐标转换为与基于主要对象图形的坐标系重合的变换器; 基于所输入的主要对象图形的几何信息和每个坐标变换的辅助对象图形的处理器,通过使用用于获取碰撞点,碰撞存在信息和主要和次要对象图形之间的碰撞深度的处理器 由主要和次要对象图形的几何信息属性确定的碰撞检测操作技术; 第二存储单元,用于分别存储冲突信息,其中更新之前/之后的碰撞深度分别存储在两个区域中; 以及更新单元,用于每当从处理器新输出时更新碰撞点和冲突存在信息,其中基于与先前存储的冲突深度的比较结果来更新冲突深度。