公开(公告)号：US08232996B2

公开(公告)日：2012-07-31

申请号：US12468423

申请日：2009-05-19

申请人： Timothee Bailloeul ,  Caizhi Zhu ,  Yinghul Xu

发明人： Timothee Bailloeul ,  Caizhi Zhu ,  Yinghul Xu

IPC分类号： G06T11/20 ,  G06F15/16

CPC分类号： G06F17/30256 ,  G06F17/30265 ,  G06K9/6247

摘要： A first image having annotations is segmented into one or more image regions. Image feature vectors and text feature vectors are extracted from all the image regions to obtain an image feature matrix and a text feature matrix. The image feature matrix and the text feature matrix are projected into a sub-space to obtain the projected image feature matrix and the text feature matrix. The projected image feature matrix and the text feature matrix are stored. First links between the image regions, second links between the first image and the image regions, third links between the first image and the annotations, and fourth links between the annotations are established. Weights of all the links are calculated. A graph showing a triangular relationship between the first image, image regions, and annotations is obtained based on all the links and the weights of the links.

摘要翻译： 具有注释的第一图像被分割成一个或多个图像区域。 从所有图像区域提取图像特征向量和文本特征向量以获得图像特征矩阵和文本特征矩阵。 将图像特征矩阵和文本特征矩阵投影到子空间中以获得投影图像特征矩阵和文本特征矩阵。 存储投影图像特征矩阵和文本特征矩阵。 建立图像区域之间的第一链接，第一图像和图像区域之间的第二链接，第一图像和注释之间的第三链接以及注释之间的第四链接。 计算所有链接的重量。 基于链接的所有链接和权重，获得显示第一图像，图像区域和注释之间的三角形关系的图形。

公开(公告)号：US20090289942A1

公开(公告)日：2009-11-26

申请号：US12468423

申请日：2009-05-19

申请人： Timothee Bailloeul ,  Caizhi Zhu ,  Yinghui Xu

发明人： Timothee Bailloeul ,  Caizhi Zhu ,  Yinghui Xu

IPC分类号： G06T11/20 ,  G06K9/46 ,  G06K9/36

CPC分类号： G06F17/30256 ,  G06F17/30265 ,  G06K9/6247

摘要： A first image having annotations is segmented into one or more image regions. Image feature vectors and text feature vectors are extracted from all the image regions to obtain an image feature matrix and a text feature matrix. The image feature matrix and the text feature matrix are projected into a sub-space to obtain the projected image feature matrix and the text feature matrix. The projected image feature matrix and the text feature matrix are stored. First links between the image regions, second links between the first image and the image regions, third links between the first image and the annotations, and fourth links between the annotations are established. Weights of all the links are calculated. A graph showing a triangular relationship between the first image, image regions, and annotations is obtained based on all the links and the weights of the links.

摘要翻译： 具有注释的第一图像被分割成一个或多个图像区域。 从所有图像区域提取图像特征向量和文本特征向量以获得图像特征矩阵和文本特征矩阵。 将图像特征矩阵和文本特征矩阵投影到子空间中以获得投影图像特征矩阵和文本特征矩阵。 存储投影图像特征矩阵和文本特征矩阵。 建立图像区域之间的第一链接，第一图像和图像区域之间的第二链接，第一图像和注释之间的第三链接以及注释之间的第四链接。 计算所有链接的重量。 基于链接的所有链接和权重，获得显示第一图像，图像区域和注释之间的三角形关系的图形。

公开(公告)号：US20110225172A1

公开(公告)日：2011-09-15

申请号：US13033016

申请日：2011-02-23

申请人： Yuan LIU ,  Gang Wang ,  Tao Li ,  Yinghui Xu ,  Caizhi Zhu

发明人： Yuan LIU ,  Gang Wang ,  Tao Li ,  Yinghui Xu ,  Caizhi Zhu

IPC分类号： G06F17/30

CPC分类号： G06F17/30265

摘要： Disclosed are a system, a method, and a computer-readable medium for seeking representative images in an image set. The method comprises a text feature extracting step of extracting text features of each of the plural images; a diversity data obtaining step of obtaining diversity data of the image set based on the text features; a representative score calculating method of calculating a representative score of each of the plural images based on the diversity data; and a representative image selecting step of selecting one or more of the images in the image set based on the representative score of the corresponding images.

摘要翻译： 公开了一种用于在图像集中寻找代表性图像的系统，方法和计算机可读介质。 该方法包括提取多个图像中的每一个的文本特征的文本特征提取步骤; 分集数据获取步骤，基于所述文本特征获得所述图像集合的分集数据; 基于分集数据计算多个图像中的每一个的代表分数的代表分数计算方法; 以及代表图像选择步骤，基于相应图像的代表性分数来选择图像集中的一个或多个图像。

公开(公告)号：US08204889B2

公开(公告)日：2012-06-19

申请号：US13033016

申请日：2011-02-23

申请人： Yuan Liu ,  Gang Wang ,  Tao Li ,  Yinghui Xu ,  Caizhi Zhu

发明人： Yuan Liu ,  Gang Wang ,  Tao Li ,  Yinghui Xu ,  Caizhi Zhu

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30265

摘要： System, method, and computer-readable medium for seeking representative images in an image set. Text features of each of the plural images are extracted. Diversity data of the image set is obtained based on the text features. A representative score of each of the plural images is calculated based on the diversity data. One or more of the images in the image set is selected as a representative image based on the representative score of the corresponding images.

摘要翻译： 用于在图像集中寻找代表性图像的系统，方法和计算机可读介质。 提取多个图像中的每一个的文本特征。 基于文本特征获得图像集合的分集数据。 基于分集数据计算多个图像中的每一个的代表分数。 基于相应图像的代表性分数，选择图像集中的一个或多个图像作为代表图像。