公开(公告)号：US20110110581A1

公开(公告)日：2011-05-12

申请号：US12912211

申请日：2010-10-26

申请人： Hyun Seung YANG ,  Kyu Sung CHO ,  Jae Sang YOO ,  Jin Ki JUNG

发明人： Hyun Seung YANG ,  Kyu Sung CHO ,  Jae Sang YOO ,  Jin Ki JUNG

IPC分类号： G06K9/00

CPC分类号： G06K9/00201 ,  G06K9/469 ,  G06K9/6211 ,  G06K9/6278

摘要： Disclosed herein is a three-dimensional (3D) object recognition system and method. The 3D object recognition system includes a storage unit for storing an extended randomized forest in which a plurality of randomized trees is included and each of the randomized trees includes a plurality of leaf nodes, training means for extracting a plurality of keypoints from a training target object image, and calculating and storing an object recognition posterior probability distribution and training target object-based keypoint matching posterior probability distributions, and matching means for extracting a plurality of keypoints from a matching target object image, matching the extracted keypoints to a plurality of leaf nodes, recognizing an object using the object recognition posterior probability distributions, and matching the keypoints to keypoints of the recognized object using training target object-based keypoint matching posterior probability distributions stored at the matched leaf nodes.

摘要翻译： 本文公开了三维（3D）对象识别系统和方法。 3D对象识别系统包括存储单元，用于存储其中包括多个随机化树的扩展随机林，并且每个随机化树包括多个叶节点;训练装置，用于从训练对象对象中提取多个关键点 图像，以及计算和存储对象识别后验概率分布和训练目标对象的关键点匹配后验概率分布，以及匹配装置，用于从匹配的目标对象图像中提取多个关键点，将提取的关键点与多个叶节点匹配 使用对象识别后验概率分布识别对象，并且使用存储在匹配叶节点处的训练目标基于对象的关键点匹配后验概率分布来将关键点与识别对象的关键点进行匹配。

公开(公告)号：US20090196506A1

公开(公告)日：2009-08-06

申请号：US12324770

申请日：2008-11-26

申请人： Hyun Seung YANG ,  Yeong Nam CHAE ,  Ji Nyun CHUNG

发明人： Hyun Seung YANG ,  Yeong Nam CHAE ,  Ji Nyun CHUNG

IPC分类号： G06K9/46

CPC分类号： G06K9/00228

摘要： Disclosed herein is a subwindow setting method for a face detector for detecting whether one or more facial images exist in each of subwindows having a set size while sequentially setting the subwindows in the width direction of an input image. A scan interval between two neighboring subwindows under consideration in the width direction is determined based on the facial color density of a first subwindow of the two neighboring subwindows. Further, a scan interval between the first and second rows in a height direction of the input image is determined based on the facial color density of the subwindows included in the first row.

摘要翻译： 这里公开了一种用于面部检测器的子窗口设置方法，用于检测在输入图像的宽度方向上顺序地设置子窗口时是否存在具有设定尺寸的子窗口中的每一个中的一个或多个面部图像。 基于两个相邻子窗口的第一子窗口的面部颜色浓度来确定在宽度方向上考虑的两个相邻子窗口之间的扫描间隔。 此外，基于包括在第一行中的子窗口的面部颜色浓度来确定输入图像的高度方向上的第一行和第二行之间的扫描间隔。