专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20080298766A1 Interactive Photo Annotation Based on Face Clustering 有权
标题翻译：基于人脸聚类的互动照片注释
公开(公告)号：US20080298766A1
公开(公告)日：2008-12-04
申请号：US11754933
申请日：2007-05-29
申请人： Fang Wen , Rong Xiao , Qiong Yang , Xiaoou Tang
发明人： Fang Wen , Rong Xiao , Qiong Yang , Xiaoou Tang
IPC分类号： H04N5/91
CPC分类号： G06F17/30259 , G06F17/3028
摘要： An interactive photo annotation method uses clustering based on facial similarities to improve annotation experience. The method uses a face recognition algorithm to extract facial features of a photo album and cluster the photos into multiple face groups based on facial similarity. The method annotates a face group collectively using annotations, such as name identifiers, in one operation. The method further allows merging and splitting of face groups. Special graphical user interfaces, such as displays in a group view area and a thumbnail area and drag-and-drop features, are used to further improve the annotation experience.
摘要翻译：交互式照片注释方法使用基于面部相似度的聚类来改进注释体验。该方法使用面部识别算法提取相册的面部特征，并根据面部相似度将照片聚类成多个面部组。该方法在一个操作中使用注释（例如名称标识符）集体使用面部组。该方法还允许面组的合并和分割。使用特殊的图形用户界面，例如组视图区域中的显示和缩略图区域以及拖放功能，以进一步改进注释体验。

2. 发明授权

US08189880B2 Interactive photo annotation based on face clustering 有权
标题翻译：基于面部聚类的交互式照片注释
公开(公告)号：US08189880B2
公开(公告)日：2012-05-29
申请号：US11754933
申请日：2007-05-29
申请人： Fang Wen , Rong Xiao , Qiong Yang , Xiaoou Tang
发明人： Fang Wen , Rong Xiao , Qiong Yang , Xiaoou Tang
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06F17/30259 , G06F17/3028
摘要： An interactive photo annotation method uses clustering based on facial similarities to improve annotation experience. The method uses a face recognition algorithm to extract facial features of a photo album and cluster the photos into multiple face groups based on facial similarity. The method annotates a face group collectively using annotations, such as name identifiers, in one operation. The method further allows merging and splitting of face groups. Special graphical user interfaces, such as displays in a group view area and a thumbnail area and drag-and-drop features, are used to further improve the annotation experience.
摘要翻译：交互式照片注释方法使用基于面部相似度的聚类来改进注释体验。该方法使用面部识别算法提取相册的面部特征，并根据面部相似度将照片聚类成多个面部组。该方法在一个操作中使用注释（例如名称标识符）集体使用面部组。该方法还允许面组的合并和分割。使用特殊的图形用户界面，例如组视图区域中的显示和缩略图区域以及拖放功能，以进一步改进注释体验。

3. 发明授权

US08644600B2 Learning object cutout from a single example 有权
标题翻译：从一个例子学习对象剪切
公开(公告)号：US08644600B2
公开(公告)日：2014-02-04
申请号：US11810595
申请日：2007-06-05
申请人： Qiong Yang , Fang Wen , Xiaoou Tang
发明人： Qiong Yang , Fang Wen , Xiaoou Tang
IPC分类号： G06K9/00
CPC分类号： G06K9/621 , G06T7/11 , G06T7/12 , G06T7/162 , G06T7/174 , G06T7/194 , G06T7/90 , G06T2207/10024 , G06T2207/20072 , G06T2207/20081 , G06T2207/20121
摘要： Systems and methods are described for learning visual object cutout from a single example. In one implementation, an exemplary system determines the color context near each block in a model image to create an appearance model. The system also learns color sequences that occur across visual edges in the model image to create an edge profile model. The exemplary system then infers segmentation boundaries in unknown images based on the appearance model and edge profile model. In one implementation, the exemplary system minimizes the energy in a graph-cut model where the appearance model is used for data energy and the edge profile is used to modulate edges. The system is not limited to images with nearly identical foregrounds or backgrounds. Some variations in scale, rotation, and viewpoint are allowed.
摘要翻译：描述了从单个示例中学习视觉对象切割的系统和方法。在一个实现中，示例性系统确定模型图像中每个块附近的颜色上下文以创建外观模型。该系统还学习在模型图像中跨视觉边缘发生的颜色序列，以创建边缘轮廓模型。然后，示例性系统基于外观模型和边缘轮廓模型来推断未知图像中的分割边界。在一个实现中，示例性系统最小化图形切割模型中的能量，其中外观模型用于数据能量，并且边缘轮廓用于调制边缘。该系统不限于具有几乎相同的前景或背景的图像。允许在比例尺，旋转角度和视角上有一些变化。

4. 发明申请

US20080304735A1 Learning object cutout from a single example 有权
标题翻译：从一个例子学习对象剪切
公开(公告)号：US20080304735A1
公开(公告)日：2008-12-11
申请号：US11810595
申请日：2007-06-05
申请人： Qiong Yang , Fang Wen , Xiaoou Tang
发明人： Qiong Yang , Fang Wen , Xiaoou Tang
IPC分类号： G06K9/00
CPC分类号： G06K9/621 , G06T7/11 , G06T7/12 , G06T7/162 , G06T7/174 , G06T7/194 , G06T7/90 , G06T2207/10024 , G06T2207/20072 , G06T2207/20081 , G06T2207/20121
摘要： Systems and methods are described for learning visual object cutout from a single example. In one implementation, an exemplary system determines the color context near each block in a model image to create an appearance model. The system also learns color sequences that occur across visual edges in the model image to create an edge profile model. The exemplary system then infers segmentation boundaries in unknown images based on the appearance model and edge profile model. In one implementation, the exemplary system minimizes the energy in a graph-cut model where the appearance model is used for data energy and the edge profile is used to modulate edges. The system is not limited to images with nearly identical foregrounds or backgrounds. Some variations in scale, rotation, and viewpoint are allowed.
摘要翻译：描述了从单个示例中学习视觉对象切割的系统和方法。在一个实现中，示例性系统确定模型图像中每个块附近的颜色上下文以创建外观模型。该系统还学习在模型图像中跨视觉边缘发生的颜色序列，以创建边缘轮廓模型。然后，示例性系统基于外观模型和边缘轮廓模型来推断未知图像中的分割边界。在一个实现中，示例性系统最小化图形切割模型中的能量，其中外观模型用于数据能量，并且边缘轮廓用于调制边缘。该系统不限于具有几乎相同的前景或背景的图像。允许在比例尺，旋转角度和视角上有一些变化。

5. 发明授权

US08014572B2 Face annotation framework with partial clustering and interactive labeling 有权
标题翻译：面部注释框架，具有部分聚类和交互式标签
公开(公告)号：US08014572B2
公开(公告)日：2011-09-06
申请号：US11760641
申请日：2007-06-08
申请人： Rong Xiao , Fang Wen , Xiaoou Tang
发明人： Rong Xiao , Fang Wen , Xiaoou Tang
IPC分类号： G06K9/00
CPC分类号： G06K9/6226 , G06F17/30017 , G06F17/30265 , G06F17/3028 , G06K9/00288 , G06K9/6254
摘要： Systems and methods are described for a face annotation framework with partial clustering and interactive labeling. In one implementation, an exemplary system automatically groups some images of a collection of images into clusters, each cluster mainly including images that contain a person's face associated with that cluster. After an initial user-labeling of each cluster with the person's name or other label, in which the user may also delete/label images that do not belong in the cluster, the system iteratively proposes subsequent clusters for the user to label, proposing clusters of images that when labeled, produce a maximum information gain at each iteration and minimize the total number of user interactions for labeling the entire collection of images.
摘要翻译：描述了具有部分聚类和交互式标签的面部注释框架的系统和方法。在一个实现中，示例性系统自动地将图像集合的一些图像分组成群集，每个群集主要包括包含与该群集相关联的人脸的图像。在用户的姓名或其他标签对每个集群进行初始用户标签之后，用户还可以在其中删除/标记不属于集群的图像，系统迭代地提出用于用户标签的后续集群，提出集群标记后的图像在每次迭代时产生最大的信息增益，并最大限度地减少用户标记整个图像集合的总体交互次数。

6. 发明申请

US20080304755A1 Face Annotation Framework With Partial Clustering And Interactive Labeling 有权
标题翻译：面部注释框架与部分聚类和交互式标签
公开(公告)号：US20080304755A1
公开(公告)日：2008-12-11
申请号：US11760641
申请日：2007-06-08
申请人： Rong Xiao , Fang Wen , Xiaoou Tang
发明人： Rong Xiao , Fang Wen , Xiaoou Tang
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6226 , G06F17/30017 , G06F17/30265 , G06F17/3028 , G06K9/00288 , G06K9/6254
摘要： Systems and methods are described for a face annotation framework with partial clustering and interactive labeling. In one implementation, an exemplary system automatically groups some images of a collection of images into clusters, each cluster mainly including images that contain a person's face associated with that cluster. After an initial user-labeling of each cluster with the person's name or other label, in which the user may also delete/label images that do not belong in the cluster, the system iteratively proposes subsequent clusters for the user to label, proposing clusters of images that when labeled, produce a maximum information gain at each iteration and minimize the total number of user interactions for labeling the entire collection of images.
摘要翻译：描述了具有部分聚类和交互式标签的面部注释框架的系统和方法。在一个实现中，示例性系统自动地将图像集合的一些图像分组成群集，每个群集主要包括包含与该群集相关联的人脸的图像。在用户的姓名或其他标签对每个集群进行初始用户标签之后，用户还可以在其中删除/标记不属于集群的图像，系统迭代地提出用于用户标签的后续集群，提出集群标记后的图像在每次迭代时产生最大的信息增益，并最大限度地减少用户标记整个图像集合的总体交互次数。

7. 发明申请

US20070189611A1 Bayesian Competitive Model Integrated With a Generative Classifier for Unspecific Person Verification 有权
标题翻译：贝叶斯竞争模型与用于非特定人员验证的生成分类器集成
公开(公告)号：US20070189611A1
公开(公告)日：2007-08-16
申请号：US11276112
申请日：2006-02-14
申请人： Qiong Yang , Xiaoou Tang
发明人： Qiong Yang , Xiaoou Tang
IPC分类号： G06K9/62
CPC分类号： G06K9/6278 , G06K9/6292
摘要： A Bayesian competitive model integrated with a generative classifier for unspecific person verification is described. In one aspect, a competitive measure for verification of an unspecific person is calculated using a discriminative classifier. The discriminative classifier is based on a Bayesian competitive model that is adaptable to unknown new classes. The Bayesian competitive model is integrated with a generative verification in view of a set of confidence criteria to make a decision regarding verification of the unspecific person.
摘要翻译：描述了与非特定人员验证的生成分类器集成的贝叶斯竞争模型。一方面，使用歧视性分类器来计算非特异性人的验证的竞争措施。歧视性分类器基于贝叶斯竞争模型，适用于未知的新类。贝叶斯竞争模式与生成验证相结合，鉴于一套信心标准，对非特定人员的验证作出决定。

8. 发明申请

US20070086646A1 Occlusion Handling in Stero Imaging 有权
标题翻译： Stero成像中的闭塞处理
公开(公告)号：US20070086646A1
公开(公告)日：2007-04-19
申请号：US11462342
申请日：2006-08-03
申请人： Qiong Yang , Yi Deng , Xiaoou Tang , Xueyin Lin
发明人： Qiong Yang , Yi Deng , Xiaoou Tang , Xueyin Lin
IPC分类号： G06K9/00
CPC分类号： G06K9/20 , G06K9/6207 , G06K2209/40 , G06T7/593 , G06T2207/10012 , G06T2207/20016
摘要： The handling of occlusions in stereo imaging is disclosed. In one implementation, an association between a discontinuity in one stereo image and an occlusion in a second stereo image is utilized. In such an implementation, the first and second stereo images are segmented. A mapping of a discontinuity within the second stereo image is used to form at least part of a boundary of an occlusion in the first stereo image. The mapped discontinuity is found at a boundary between two segments in the second stereo image, and once mapped, divides a segment in the first stereo image into two patches. An energy calculation is made in an iterative manner, alternating with changes to a solution with the disparities and occlusions of the patches. Upon minimization, disparities and occlusions at the patch and pixel level are available.
摘要翻译：公开了立体成像中遮挡物的处理。在一个实现中，利用一个立体图像中的不连续性和第二立体图像中的遮挡之间的关联。在这种实现中，分割第一和第二立体图像。使用第二立体图像内的不连续性的映射来形成第一立体图像中的遮挡的边界的至少一部分。映射的不连续性位于第二立体图像中的两个段之间的边界处，一旦映射，则将第一立体图像中的段划分成两个补丁。以迭代的方式进行能量计算，并与补丁的差异和闭塞的解决方案的变化交替进行。在最小化时，可以使用补丁和像素级别的差异和遮挡。

9. 发明授权

US08300085B2 Occlusion handling in stereo imaging 有权
标题翻译：立体成像中的闭塞处理
公开(公告)号：US08300085B2
公开(公告)日：2012-10-30
申请号：US11462342
申请日：2006-08-03
申请人： Qiong Yang , Yi Deng , Xiaoou Tang , Xueyin Lin
发明人： Qiong Yang , Yi Deng , Xiaoou Tang , Xueyin Lin
IPC分类号： H04N15/00 , H04N13/00 , G06K9/00
CPC分类号： G06K9/20 , G06K9/6207 , G06K2209/40 , G06T7/593 , G06T2207/10012 , G06T2207/20016
摘要： The handling of occlusions in stereo imaging is disclosed. In one implementation, an association between a discontinuity in one stereo image and an occlusion in a second stereo image is utilized. In such an implementation, the first and second stereo images are segmented. A mapping of a discontinuity within the second stereo image is used to form at least part of a boundary of an occlusion in the first stereo image. The mapped discontinuity is found at a boundary between two segments in the second stereo image, and once mapped, divides a segment in the first stereo image into two patches. An energy calculation is made in an iterative manner, alternating with changes to a solution with the disparities and occlusions of the patches. Upon minimization, disparities and occlusions at the patch and pixel level are available.
摘要翻译：公开了立体成像中遮挡物的处理。在一个实现中，利用一个立体图像中的不连续性和第二立体图像中的遮挡之间的关联。在这种实现中，分割第一和第二立体图像。使用第二立体图像内的不连续性的映射来形成第一立体图像中的遮挡的边界的至少一部分。在第二立体图像中的两个段之间的边界处发现映射的不连续性，并且一旦映射，将第一立体图像中的段划分成两个补丁。以迭代的方式进行能量计算，并与补丁的差异和闭塞的解决方案的变化交替进行。在最小化时，可以使用补丁和像素级别的差异和遮挡。

10. 发明授权

US08045800B2 Active segmentation for groups of images 有权
标题翻译：主动分割图像组
公开(公告)号：US08045800B2
公开(公告)日：2011-10-25
申请号：US12025703
申请日：2008-02-04
申请人： Xiaoou Tang , Qiong Yang
发明人： Xiaoou Tang , Qiong Yang
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/38 , G06K2009/366
摘要： Systems and methods of segmenting images are disclosed herein. The similarity of images in a set of images is compared. A group of images is selected from the set of images. The images in the group of images are selected based on compared similarities among the images. An informative image is selected from the group of images. User-defined semantic information of the informative image is received. The group of images as a graph is modeled as a graph. Each image in the group of images denotes a node in the graph. Edges of the graph denote a foreground relationship between images or a background relationship between images. One or more images in the group of images are automatically segmented by propagating the semantic information of the informative image to images in the group of images having a corresponding graph node that is related to a graph node corresponding to the informative image. Segmentation results can be refined according to user provided image semantics.
摘要翻译：本文公开了分割图像的系统和方法。比较一组图像中图像的相似度。从该组图像中选择一组图像。基于图像中的相似度来选择图像组中的图像。从图像组中选择信息图像。收到信息图像的用户定义语义信息。作为图形的图像组被建模为图形。图像组中的每个图像表示图中的一个节点。图的边缘表示图像之间的前景关系或图像之间的背景关系。通过将信息图像的语义信息传播到具有与对应于信息图像的图形节点相关联的对应图形节点的图像组中的图像来自动分割图像组中的一个或多个图像。分割结果可以根据用户提供的图像语义进行细化。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式