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
    • 141. 发明授权
    • Method and system for face detection using pattern classifier
    • 使用模式分类器进行面部检测的方法和系统
    • US07447338B2
    • 2008-11-04
    • US10621356
    • 2003-07-18
    • Tae-kyun Kim
    • Tae-kyun Kim
    • G06K9/00
    • G06K9/6269G06K9/00241
    • A system and method for detecting a face using a pattern classifier learning face images and near face images are provided. The system includes a basis vector extractor, which receives a plurality of face images and a plurality of near-face images and extracts a plurality of face basis vectors expressing the face images and a plurality of near-face basis vectors expressing the near-face images; a feature vector extractor, which extracts face feature vectors and near-face feature vectors by projecting the face images and the near-face images upon the face and near-face feature vectors and projects an image, which is input for face detection, upon the basis vectors to extract the feature vector of the input image; a clustering unit, which classifies the face feature vectors and the near-face feature vectors into predetermined sub-classes and outputs a sub-class number of a sub-class including the feature vector of the input image among the sub-classes; a pattern classifier trainer, which trains each pattern classifier corresponding to a certain sub-class using face feature vectors and near-face feature vectors, which are included in the sub-class; and a face determiner, which applies the feature vector of the input image to the pattern classifier corresponding to the sub-class including the feature vector of the input image and determines whether the input image is a face image using the pattern classifier.
    • 提供一种使用模式分类器学习面部图像和近脸图像来检测面部的系统和方法。 该系统包括基矢量提取器,其接收多个面部图像和多个近脸图像,并且提取表示面部图像的多个面部基本向量和表示近脸图像的多个近脸基本向量 ; 特征向量提取器,其通过将脸部图像和近脸图像投影在脸部和近脸特征向量上并且将用于面部检测的输入的图像投影到脸部特征向量和近脸特征向量上来提取面部特征向量和近脸特征向量 基本向量来提取输入图像的特征向量; 聚类单元,将面部特征向量和近脸特征向量分类为预定的子类,并且输出子类中包含输入图像的特征向量的子类的子类数; 模式分类器训练器,其使用包括在子类中的面部特征向量和近脸特征向量来训练与特定子类对应的每个模式分类器; 以及面部确定器,其将输入图像的特征向量应用于与包括输入图像的特征向量的子类相对应的模式分类器,并使用模式分类器来确定输入图像是否是面部图像。
    • 149. 发明申请
    • Coil nailing device for construction finishing materials
    • 建筑装饰材料线圈钉装置
    • US20080110956A1
    • 2008-05-15
    • US12007402
    • 2008-01-10
    • Bo-Seob ChoGil-Sub SongJae KimIn HwangMyung-Kyun KimSang LeeJong-Yeol Han
    • Bo-Seob ChoGil-Sub SongJae KimIn HwangMyung-Kyun KimSang LeeJong-Yeol Han
    • B27F7/00
    • B25C5/1658B25C5/1665
    • A coil nailing device for finishing materials is invented that comprises a standby part for temporarily retaining and loading the nails into a muzzle. A door is installed adjacent to the standby part to check the nail supply. A door latch consists of a hook, coil spring and latch hinge shaft. The door and door latch are operated in the lateral direction, perpendicular to the axis of the main body. The muzzle consists of an adapter, lever arm and a pair of arc-shaped sliding grooves formed on both lateral surfaces. The adapter is attachable to the nose of the main body. A clearance setting device is designed to allow the use of various sizes of nails by setting the depth of the magazine depending on the loaded nail size. An interval setting device is convenient to nail a series of shingle panels by setting the panel interval while the coil nailing device is sliding along the edge of the panels.
    • 发明了一种用于整理材料的线圈钉装置,其包括用于将钉子临时保持和装载到枪口中的备用部件。 在备用部件附近安装一个门,以检查指甲供应。 门闩由钩,螺旋弹簧和闩锁铰链组成。 门和门闩在横向方向上工作,垂直于主体的轴线。 枪口由适配器,杠杆臂和形成在两个侧面上的一对弧形滑动槽组成。 适配器可连接到主体的鼻子。 间隙设定装置被设计成允许使用各种尺寸的钉子,通过根据装载的钉子尺寸设定料仓的深度。 间隔设定装置通过在线圈钉装置沿着面板的边缘滑动的同时设置面板间隔来钉住一系列的瓦片。
    • 150. 发明申请
    • Method for generating multi-resolution three-dimensional model
    • 用于生成多分辨率三维模型的方法
    • US20080084413A1
    • 2008-04-10
    • US11811856
    • 2007-06-11
    • Soo-Kyun Kim
    • Soo-Kyun Kim
    • G06T17/00G09G5/37
    • G06T17/20
    • Disclosed is a method for generating a multi-resolution three-dimensional model, and for extracting feature lines using texture images and geometric data from a three-dimensional model. First, contours are detected for texture images using an image processing on the texture-mapped three-dimensional mesh data. With respect to geometric data, a discrete curvature is measured. The geometric data is parametrized into parameters in a two-dimensional domain, and contour images are detected using an image processing. The detected two contour images are generated into one model map, which is then reversely mapped to a reverse three-dimensional model, then next feature lines are extracted. Accordingly, a multi-resolution three-dimensional model can be generated while maintaining the extracted feature lines.
    • 公开了一种用于生成多分辨率三维模型的方法,并且用于使用纹理图像和来自三维模型的几何数据来提取特征线。 首先,使用纹理映射的三维网格数据上的图像处理来检测纹理图像的轮廓。 对于几何数据,测量离散曲率。 将几何数据参数化为二维域中的参数,并使用图像处理检测轮廓图像。 检测到的两个轮廓图像生成一个模型图,然后反向映射到反向三维模型,然后提取下一个特征线。 因此,可以在保持所提取的特征线的同时产生多分辨率三维模型。