公开(公告)号：US20100272411A1

公开(公告)日：2010-10-28

申请号：US12764350

申请日：2010-04-21

申请人： Shuichi SHIITANI ,  Masaki Ishihara ,  Takayuki Baba ,  Susumu Endo ,  Daiki Masumoto ,  Shigemi Nagata

发明人： Shuichi SHIITANI ,  Masaki Ishihara ,  Takayuki Baba ,  Susumu Endo ,  Daiki Masumoto ,  Shigemi Nagata

IPC分类号： G06K9/62 ,  H04N5/93

CPC分类号： H04N5/76 ,  G06K9/00751 ,  G11B27/105 ,  G11B27/28 ,  G11B27/34

摘要： A playback apparatus that divides the content into scenes; specifies a scene played back after a fast-forward operation or a rewind; calculates a first feature value of the scene specified by the specifying unit; divides content different from the video content into scenes and calculates second feature values, each of which corresponds to one of the scenes obtained by the second feature-value calculation unit; compares the first feature value with the second feature values and extracts a scene whose second feature value differs from the first feature value by a predetermined threshold or less; and outputs the scene extracted by the extraction unit.

摘要翻译： 将内容分割为场景的再现装置; 指定快进操作或快退后播放的场景; 计算由指定单元指定的场景的第一特征值; 将与视频内容不同的内容划分为场景，并计算第二特征值，每个特征值对应于由第二特征值计算单元获得的场景之一; 将第一特征值与第二特征值进行比较，并将其第二特征值与第一特征值不同的场景提取预定阈值以下; 并输出由提取单元提取的场景。

公开(公告)号：US08311320B2

公开(公告)日：2012-11-13

申请号：US12256970

申请日：2008-10-23

申请人： Susumu Endo ,  Takayuki Baba ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

发明人： Susumu Endo ,  Takayuki Baba ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

IPC分类号： G06K9/00

CPC分类号： G06T7/001 ,  G06T19/20 ,  G06T2207/30108 ,  G06T2219/2004 ,  G06T2219/2012 ,  G06T2219/2021

摘要： A difference emphasizing apparatus aligns a first three-dimensional model and a second three-dimensional model in orientation and position in accordance with a predetermined rule, and gets data of respective apices of the first three-dimensional model and the second three-dimensional model. Based on the gotten data, the apparatus finds a corresponding point on the first three-dimensional model, which corresponds to the apex of the second three-dimensional model in a direction of a particular axis. When the corresponding point is detected, the apparatus calculates a difference between the first three-dimensional model and the second three-dimensional model in the direction of the particular axis based on the corresponding point and the apex of the second three-dimensional model. The apparatus enlarges the difference in the direction of the particular axis, and calculates a position of the apex of the second three-dimensional model after the enlargement.

摘要翻译： 差异强调装置根据预定规则对准取向和位置处的第一三维模型和第二三维模型，并获得第一三维模型和第二三维模型的各个顶点的数据。 基于得到的数据，该装置在第一三维模型上找到对应于在特定轴的方向上的第二个三维模型的顶点的对应点。 当检测到对应点时，该装置基于第二三维模型的对应点和顶点，在特定轴的方向上计算第一三维模型和第二三维模型之间的差异。 该装置放大特定轴方向的差异，并计算放大后的第二三维模型的顶点的位置。

公开(公告)号：US20050249414A1

公开(公告)日：2005-11-10

申请号：US11182808

申请日：2005-07-18

申请人： Yusuke Uehara ,  Daiki Masumoto ,  Shuichi Shiitani ,  Susumu Endo ,  Takayuki Baba

发明人： Yusuke Uehara ,  Daiki Masumoto ,  Shuichi Shiitani ,  Susumu Endo ,  Takayuki Baba

IPC分类号： G01N21/88 ,  G06K9/00 ,  G06N5/04 ,  G06T1/00 ,  G06T7/00

CPC分类号： G01N21/8851 ,  G06T7/0004 ,  G06T2207/30164

摘要： A knowledge discovery device analyzes a relation between a feature value of an image and attribute data, and discovers a knowledge on the relation. The knowledge discovery device includes a feature-value extraction unit that extracts, as a feature value, each degree of changes in luminance of frequency components at each position on the image, from image data, a relation analysis unit that analyzes a relation between the feature value and attribute data, and a rule generation unit that generates an association rule using content of the feature value having a correlation value not more than a predetermined correlation value and content of the attribute data.

摘要翻译： 知识发现设备分析图像的特征值与属性数据之间的关系，并且发现关于该关系的知识。 所述知识发现装置包括：特征值提取单元，从图像数据中提取作为特征值的每个位置上的频率分量的亮度变化的每个变化度，分析所述特征的关系的关系分析单元 值和属性数据，以及规则生成单元，其使用具有不大于预定相关值的相关值的特征值的内容和属性数据的内容来生成关联规则。

公开(公告)号：US20090110297A1

公开(公告)日：2009-04-30

申请号：US12256970

申请日：2008-10-23

申请人： Susumu Endo ,  Takayuki Baba ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

发明人： Susumu Endo ,  Takayuki Baba ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

IPC分类号： G06K9/68

CPC分类号： G06T7/001 ,  G06T19/20 ,  G06T2207/30108 ,  G06T2219/2004 ,  G06T2219/2012 ,  G06T2219/2021

摘要： A difference emphasizing apparatus aligns a first three-dimensional model and a second three-dimensional model in orientation and position in accordance with a predetermined rule, and gets data of respective apices of the first three-dimensional model and the second three-dimensional model. Based on the gotten data, the apparatus finds a corresponding point on the first three-dimensional model, which corresponds to the apex of the second three-dimensional model in a direction of a particular axis. When the corresponding point is detected, the apparatus calculates a difference between the first three-dimensional model and the second three-dimensional model in the direction of the particular axis based on the corresponding point and the apex of the second three-dimensional model. The apparatus enlarges the difference in the direction of the particular axis, and calculates a position of the apex of the second three-dimensional model after the enlargement.

摘要翻译： 差异强调装置根据预定规则对准取向和位置处的第一三维模型和第二三维模型，并获得第一三维模型和第二三维模型的各个顶点的数据。 基于得到的数据，该装置在第一三维模型上找到对应于在特定轴的方向上的第二个三维模型的顶点的对应点。 当检测到对应点时，该装置基于第二三维模型的对应点和顶点，在特定轴的方向上计算第一三维模型和第二三维模型之间的差异。 该装置放大特定轴方向的差异，并计算放大后的第二三维模型的顶点的位置。

公开(公告)号：US20050210019A1

公开(公告)日：2005-09-22

申请号：US11124107

申请日：2005-05-09

申请人： Yusuke Uehara ,  Daiki Masumoto ,  Shuichi Shiitani ,  Susumu Endo ,  Takayuki Baba

发明人： Yusuke Uehara ,  Daiki Masumoto ,  Shuichi Shiitani ,  Susumu Endo ,  Takayuki Baba

IPC分类号： G06F17/30

CPC分类号： G06F16/5838

摘要： An image retrieval apparatus includes an extracting unit that extracts a plurality of feature values from a key image, a determining unit that determines presence or absence of similarity based on whether the similarity fitted to the human's feeling regarding the similarity is calculated for the type of each feature, a calculating unit that calculates a similarity between the key image and each of a plurality of target images based on a result of determination obtained by the determining unit, and an selecting and outputting unit that selects and outputs image data that matches with the similarity calculated by the calculating unit.

摘要翻译： 图像检索装置包括提取单元，其从关键图像中提取多个特征值，确定单元，其基于是否针对每个类型的类型计算与人的感觉相似度的相似度是否相似度来确定是否存在相似性 特征，计算单元，其基于由所述确定单元获得的确定结果来计算所述关键图像与所述多个目标图像中的每一个之间的相似度;以及选择和输出单元，其选择并输出与所述相似性匹配的图像数据 由计算单位计算。

公开(公告)号：US20050179694A1

公开(公告)日：2005-08-18

申请号：US10882616

申请日：2004-06-30

申请人： Rujie Liu ,  Takayuki Baba ,  Susumu Endo ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

发明人： Rujie Liu ,  Takayuki Baba ,  Susumu Endo ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

IPC分类号： G06F17/50 ,  G06F15/80 ,  G06F17/30 ,  G06K9/48 ,  G06K9/68 ,  G06T1/00 ,  G06T7/60 ,  G09G5/00

CPC分类号： G06K9/469 ,  G06F17/30259 ,  G06K9/4638 ,  Y10S707/99933 ,  Y10S707/99937

摘要： After thinning an input image (drawing), a primitive is extracted. First, a rough primitive is extracted, and then the rough primitive becomes a primitive in a merge-split process according to a greedy strategy. Based on the primitive and the spatial correlation among primitives, an attribute graph describing the contents and the structure of the drawing is generated. The attribute graph is generated using a modified Delaunay triangle and an attribute set. An attribute graph having an attribute set is generated for each of an inquiry drawing and a comparison drawing which are compared with each other, thereby perform drawing comparison.

摘要翻译： 在输入图像（图形）变薄之后，提取原始图形。 首先，提取一个粗略的原语，然后根据贪心策略，粗略的原语成为合并拆分过程中的原语。 基于原语之间的原语和空间相关性，生成描述图形内容和结构的属性图。 属性图使用修改的Delaunay三角形和属性集生成。 对于彼此进行比较的查询图和比较图，生成具有属性集的属性图，从而进行绘图比较。

公开(公告)号：US20050162442A1

公开(公告)日：2005-07-28

申请号：US11077195

申请日：2005-03-11

申请人： Takayuki Baba ,  Daiki Masumoto ,  Yusuke Uehara ,  Shuichi Shiitani ,  Susumu Endo

发明人： Takayuki Baba ,  Daiki Masumoto ,  Yusuke Uehara ,  Shuichi Shiitani ,  Susumu Endo

IPC分类号： G01D5/00 ,  G06K9/00 ,  G06T7/00 ,  G06T7/20 ,  G09G5/00 ,  G09G5/02

CPC分类号： H04N21/23418 ,  G06K9/00711 ,  G06T7/20 ,  G06T7/73

摘要： A target object appearing position display apparatus is constructed to include an object detecting part for detecting one or a plurality of specified target objects with respect to each frame of a movie, a position data holding part for holding position data of each target object that is detected, an appearing frequency computing part for computing an appearing frequency of each target object for each position, and an intensity display part for displaying an appearing frequency of each target object by an intensity value of a corresponding pixel.

摘要翻译： 目标对象出现位置显示装置被构造为包括用于检测关于电影的每个帧的一个或多个指定目标对象的对象检测部分，用于保持检测到的每个目标对象的位置数据的位置数据保持部分 ，用于计算每个位置的每个目标对象的出现频率的出现频率计算部分，以及用于通过相应像素的强度值显示每个目标对象的出现频率的强度显示部分。

公开(公告)号：US08275780B2

公开(公告)日：2012-09-25

申请号：US11064952

申请日：2005-02-25

申请人： Takayuki Baba ,  Susumu Endo ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

发明人： Takayuki Baba ,  Susumu Endo ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30038

摘要： A rule discovery program which enables discovery of a rule by automatically searching for a feature portion which is effective for generation of a rule in multimedia data. When sample data items are inputted, a search unit selects evaluation positions on a data array constituting each of the sample data items so as to generate a selection pattern. Next, an integration unit integrates the evaluation positions in the selection pattern so as to generate a predetermined number of evaluation regions, and a rule-candidate generation unit generates a rule candidate indicating a relationship common to the sample data items. A rule-candidate evaluation unit evaluates the generated rule candidate, and an output unit outputs, as a rule, the rule candidate when the rule candidate satisfies a predetermined criterion.

摘要翻译： 一种规则发现程序，其能够通过自动搜索对于在多媒体数据中生成规则有效的特征部分来发现规则。 当输入采样数据项时，搜索单元选择构成每个样本数据项的数据阵列上的评估位置，以产生选择模式。 接下来，积分单元将选择模式中的评价位置进行积分，以产生预定数量的评价区域，规则候选生成单元生成表示与样本数据项共同的关系的规则候选。 规则候选评估单元评估生成的规则候选，并且当规则候选满足预定标准时，输出单元通常输出规则候选。

公开(公告)号：US20060095411A1

公开(公告)日：2006-05-04

申请号：US11064952

申请日：2005-02-25

申请人： Takayuki Baba ,  Susumu Endo ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

发明人： Takayuki Baba ,  Susumu Endo ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

IPC分类号： G06F17/30

CPC分类号： G06F17/30038

摘要： A rule discovery program which enables discovery of a rule by automatically searching for a feature portion which is effective for generation of a rule in multimedia data. When sample data items are inputted, a search unit selects evaluation positions on a data array constituting each of the sample data items so as to generate a selection pattern. Next, an integration unit integrates the evaluation positions in the selection pattern so as to generate a predetermined number of evaluation regions, and a rule-candidate generation unit generates a rule candidate indicating a relationship common to the sample data items. A rule-candidate evaluation unit evaluates the generated rule candidate, and an output unit outputs, as a rule, the rule candidate when the rule candidate satisfies a predetermined criterion.

摘要翻译： 一种规则发现程序，其能够通过自动搜索对于在多媒体数据中生成规则有效的特征部分来发现规则。 当输入采样数据项时，搜索单元选择构成每个样本数据项的数据阵列上的评估位置，以产生选择模式。 接下来，积分单元将选择模式中的评价位置进行积分，以产生预定数量的评价区域，规则候选生成单元生成表示与样本数据项共同的关系的规则候选。 规则候选评估单元评估生成的规则候选，并且当规则候选满足预定标准时，输出单元通常输出规则候选。

公开(公告)号：US07716256B2

公开(公告)日：2010-05-11

申请号：US10845150

申请日：2004-05-14

申请人： Susumu Endo ,  Takayuki Baba ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

发明人： Susumu Endo ,  Takayuki Baba ,  Shuichi Shiitani ,  Yusuke Uehara ,  Daiki Masumoto

IPC分类号： G06F7/00

CPC分类号： G06F17/30876 ,  Y10S707/919 ,  Y10S707/92

摘要： An information navigation system for supporting browsing of data which are linked mutually includes an starting point determination supporter, a browsing supporter, and a positioning supporter. The starting point determination supporter supports detection of first data being a starting point for an information navigation. The browsing supporter displays the first data and second data linked to the first data as in a virtual space, to allow a user to select data to be browsed next. The positioning supporter displays a current browsing position on a map which indicates a relation between all data.

摘要翻译： 用于支持链接的数据的浏览的信息导航系统包括起点确定支持者，浏览支持者和定位支持者。 起点确定支持者支持检测作为信息导航起点的第一数据。 浏览支持者在虚拟空间中显示与第一数据链接的第一数据和第二数据，以允许用户选择接下来要浏览的数据。 定位支持者在地图上显示当前浏览位置，该位置指示所有数据之间的关系。