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. 发明授权

US07920745B2 Method and apparatus for performing constrained spectral clustering of digital image data 有权
标题翻译：用于执行数字图像数据的受限频谱聚类的方法和装置
公开(公告)号：US07920745B2
公开(公告)日：2011-04-05
申请号：US11393875
申请日：2006-03-31
申请人： Yang Song , Thomas Leung
发明人： Yang Song , Thomas Leung
IPC分类号： G06K9/62
CPC分类号： G06F17/30247 , G06K9/00288 , G06K9/00362 , G06K9/6224
摘要： A method and an apparatus process digital images. The method according to one embodiment accesses element data representing a plurality of elements belonging to a plurality of digital images; performs a similarity analysis between the elements from the plurality of elements to obtain inter-relational data results relating to the elements; and performs clustering of the plurality of elements, the step of performing clustering including incorporating in the inter-relational data results at least one hard constraint relating to elements from the plurality of elements, to obtain constrained inter-relational data results, performing a spectral analysis to obtain eigenvector results from the constrained inter-relational data results, and performing discretization of the eigenvector results using constrained clustering with a criterion to enforce the at least one hard constraint to obtain clusters.
摘要翻译：一种方法和装置处理数字图像。根据一个实施例的方法访问表示属于多个数字图像的多个元素的元素数据; 执行来自多个要素的元素之间的相似度分析，以获得与元素相关的关系数据结果; 并且执行所述多个元素的聚类，所述执行聚类的步骤包括在所述关系间数据结果中包含与来自所述多个元素的元素相关的至少一个硬约束，以获得约束的关系间数据结果，执行频谱分析从约束的关系间数据结果获得特征向量结果，以及使用具有用于强制至少一个硬约束以获得聚类的准则的约束聚类来执行特征向量结果的离散化。

2. 发明申请

US20070237355A1 Method and apparatus for adaptive context-aided human classification 有权
标题翻译：用于自适应上下文辅助人类分类的方法和装置
公开(公告)号：US20070237355A1
公开(公告)日：2007-10-11
申请号：US11393661
申请日：2006-03-31
申请人： Yang Song , Thomas Leung
发明人： Yang Song , Thomas Leung
IPC分类号： G06K9/00
CPC分类号： G06K9/00369 , G06K9/6224 , G06K9/6278
摘要： A method and an apparatus process digital images. The method according to one embodiment accesses digital data representing a plurality of digital images including a plurality of persons; performs face recognition to determine first scores relating to similarity between faces of the plurality of persons; performs clothes recognition to determine second scores relating to similarity between clothes of the plurality of persons; provides a plurality of formulas for estimating a probability of a face from the faces and a clothes from the clothes to belong to a person from the plurality of persons, wherein at least one formula of the plurality of formulas utilizes a first score and a second score, and at least one formula of the plurality of formulas utilizes only one score of a first score and a second score; and selects a formula from the plurality of formulas based on availability of a first score from the first scores for two persons from the plurality of persons, and availability of a second score from the second scores for the two persons, the selected formula estimating a probability relating to similarity of identities of the two persons.
摘要翻译：一种方法和装置处理数字图像。根据一个实施例的方法访问表示包括多个人的多个数字图像的数字数据; 执行面部识别以确定与所述多个人的面部之间的相似性相关的第一分数; 执行衣服识别以确定与多个人的衣服之间的相似性相关的第二分数; 提供多个公式，用于估计来自面部的面部的概率和来自衣服的衣服，以属于来自多个人的人，其中，多个公式的至少一个公式利用第一分数和第二分数并且所述多个公式中的至少一个公式仅使用一个第一得分和第二分数的得分; 并且基于来自所述多个人的两个人的来自所述第一分数的第一分数的可用性以及来自所述两个人的第二分数的第二分数的可用性，从所述多个公式中选择公式，所选择的公式估计概率涉及两人身份的相似性。

3. 外观设计

USD515909S1 Slot machine latch 失效
标题翻译：插槽机锁
公开(公告)号：USD515909S1
公开(公告)日：2006-02-28
申请号：US29213656
申请日：2004-09-22
申请人： Thomas Leung
设计人： Thomas Leung

4. 发明申请

US20050261270A1 Modified beta-lactamases and uses thereof 有权
标题翻译：改良的β-内酰胺酶及其用途
公开(公告)号：US20050261270A1
公开(公告)日：2005-11-24
申请号：US10401867
申请日：2003-03-31
申请人： Kwok-Yin Wong , Thomas Leung , Pak-Ho Chan
发明人： Kwok-Yin Wong , Thomas Leung , Pak-Ho Chan
IPC分类号： A61P31/04 , C12N9/86 , C12N15/55 , G01N33/573 , A61K31/397 , C12N1/21 , C12N9/82
CPC分类号： C12N9/86 , G01N33/573
摘要： A tool that can screen bacteria for β-lactamases against a panel of various antibiotics is desirable. A biosensor incorporating an indicator molecule into β-lactamases may achieve this purpose, but it requires that the attached indicator molecule must not impair the binding affinity of the protein to a great extent to provide a higher sensitivity. A modified β-lactamases with a residue on the Ω-loop or outside the Ω-loop but close to the active site of β-lactamase being replaced by a reactive residue is developed in this invention.
摘要翻译：一种能够针对一组各种抗生素筛选β-内酰胺酶细菌的工具是可取的。将指示剂分子结合到β-内酰胺酶中的生物传感器可以实现该目的，但是要求附着的指示剂分子不会在很大程度上损害蛋白质的结合亲和力以提供更高的灵敏度。在本发明中开发了具有在Omega环上的残基或Omega环外部但在反应性残基被β-内酰胺酶活性位置接近的修饰的β-内酰胺酶。

5. 发明授权

US08942468B1 Object recognition 有权
标题翻译：对象识别
公开(公告)号：US08942468B1
公开(公告)日：2015-01-27
申请号：US13448735
申请日：2012-04-17
申请人： Alexander Toshkov Toshev , King Hong Thomas Leung , Jiwoong Jack Sim
发明人： Alexander Toshkov Toshev , King Hong Thomas Leung , Jiwoong Jack Sim
IPC分类号： G06K9/62
CPC分类号： G06K9/4638 , G06K9/4642 , G06K9/6204
摘要： Techniques for a shape descriptor used for object recognition are described. Tokens of an object in digital image data are captured, where tokens can be edges, interest points or even parts. Geometric configurations of the tokens are captured by describing portions of the shape of the object. The shape of such configurations is finely quantized and each configuration from the image is assigned to a quantization bin. Objects are recognized by utilizing a number of quantization bins as features. This Abstract is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.
摘要翻译：描述用于对象识别的形状描述符的技术。捕获数字图像数据中的对象的令牌，其中令牌可以是边缘，兴趣点或甚至部分。通过描述对象的形状的部分来捕获令牌的几何配置。这种配置的形状被精细量化，并且来自图像的每个配置被分配给量化仓。通过使用多个量化仓作为特征来识别对象。提交本摘要的理解是，它不会用于解释或限制权利要求的范围或含义。

6. 发明授权

US08649613B1 Multiple-instance-learning-based video classification 有权
标题翻译：基于多实例学习的视频分类
公开(公告)号：US08649613B1
公开(公告)日：2014-02-11
申请号：US13288906
申请日：2011-11-03
申请人： Thomas Leung , Yang Song , John Zhang
发明人： Thomas Leung , Yang Song , John Zhang
IPC分类号： G06K9/62 , G06K9/54 , G06K9/60
CPC分类号： G06K9/6259 , G06K9/00724 , G06K9/6224
摘要： A classifier training system trains unified classifiers for categorizing videos representing different categories of a category graph. The unified classifiers unify the outputs of a number of separate initial classifiers trained from disparate subsets of a training set of media items. The training process divides the training set into a number of bags, and applies a boosting algorithm to the bags, thus enhancing the accuracy of the unified classifiers.
摘要翻译：分类器训练系统训练统一的分类器，用于对表示类别图表的不同类别的视频进行分类。统一的分类器统一了由训练集合的媒体项目的不同子集训练的多个单独的初始分类器的输出。培训过程将训练集划分为多个行李，并对行李采用增强算法，提高统一分类器的准确性。

7. 发明授权

US07864989B2 Method and apparatus for adaptive context-aided human classification 有权
标题翻译：用于自适应上下文辅助人类分类的方法和装置
公开(公告)号：US07864989B2
公开(公告)日：2011-01-04
申请号：US11393661
申请日：2006-03-31
申请人： Yang Song , Thomas Leung
发明人： Yang Song , Thomas Leung
IPC分类号： G06K9/00 , G06K9/54 , G06K9/60
CPC分类号： G06K9/00369 , G06K9/6224 , G06K9/6278
摘要： A method and an apparatus process digital images. The method according to one embodiment accesses digital data representing a plurality of digital images including a plurality of persons; performs face recognition to determine first scores relating to similarity between faces of the plurality of persons; performs clothes recognition to determine second scores relating to similarity between clothes of the plurality of persons; provides a plurality of formulas for estimating a probability of a face from the faces and a clothes from the clothes to belong to a person from the plurality of persons, wherein at least one formula of the plurality of formulas utilizes a first score and a second score, and at least one formula of the plurality of formulas utilizes only one score of a first score and a second score; and selects a formula from the plurality of formulas based on availability of a first score from the first scores for two persons from the plurality of persons, and availability of a second score from the second scores for the two persons, the selected formula estimating a probability relating to similarity of identities of the two persons.
摘要翻译：一种方法和装置处理数字图像。根据一个实施例的方法访问表示包括多个人的多个数字图像的数字数据; 执行面部识别以确定与所述多个人的面部之间的相似性相关的第一分数; 执行衣服识别以确定与多个人的衣服之间的相似性相关的第二分数; 提供多个公式，用于估计来自面部的面部的概率和来自衣服的衣服，以属于来自多个人的人，其中，多个公式的至少一个公式利用第一分数和第二分数并且所述多个公式中的至少一个公式仅使用一个第一得分和第二分数的得分; 并且基于来自所述多个人的两个人的来自所述第一分数的第一分数的可用性以及来自所述两个人的第二分数的第二分数的可用性，从所述多个公式中选择公式，所选择的公式估计概率涉及两人身份的相似性。

8. 发明授权

US07747045B2 Method and apparatus for diffusion based illumination normalization 有权
标题翻译：用于基于扩散的照明归一化的方法和装置
公开(公告)号：US07747045B2
公开(公告)日：2010-06-29
申请号：US11477907
申请日：2006-06-30
申请人： Troy Chinen , Thomas Leung
发明人： Troy Chinen , Thomas Leung
IPC分类号： G06K9/00
CPC分类号： G06T5/002 , G06T5/20 , G06T7/13 , G06T2207/20012 , G06T2207/20081 , G06T2207/20192
摘要： An exemplary illumination normalization method is provided which includes receiving an input image having at least one spurious edge directly resulting from illumination, performing anisotropic diffusion on the input image to form a diffusion image, and removing at the least one spurious edge using the diffusion image. Another embodiment consistent with the invention is an apparatus for performing illumination normalization in an image which includes a processor operably coupled to a memory storing input image data which contains an object of interest having at least one spurious edge directly resulting from illumination, a model of a representative object of interest, and functional processing units for controlling image processing, wherein the functional processing units further include a model based anisotropic diffusion module which predicts edge information regarding the object of interest based upon the model, and produces a reflectance estimation utilizing the predicted edge information.
摘要翻译：提供了一种示例性的照明归一化方法，其包括接收具有直接由照明产生的至少一个伪边的输入图像，在输入图像上执行各向异性扩散以形成漫射图像，以及使用扩散图像在至少一个假边缘处去除。与本发明相一致的另一实施例是用于在图像中执行照明归一化的装置，其包括可操作地耦合到存储输入图像数据的存储器的处理器，所述存储器包含感兴趣的对象，其具有直接由照明产生的至少一个伪边，以及用于控制图像处理的功能处理单元，其中所述功能处理单元还包括基于模型的各向异性扩散模块，其基于所述模型预测关于所述对象的边缘信息，并且使用所述预测边缘产生反射率估计信息。

9. 发明申请

US20070237364A1 Method and apparatus for context-aided human identification 审中-公开
标题翻译：上下文辅助人类识别的方法和装置
公开(公告)号：US20070237364A1
公开(公告)日：2007-10-11
申请号：US11394242
申请日：2006-03-31
申请人： Yang Song , Thomas Leung
发明人： Yang Song , Thomas Leung
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/00369
摘要： A method and an apparatus process digital images. The method according to one embodiment accesses digital data representing a plurality of digital images including a plurality of persons; performs face recognition to generate face recognition scores relating to similarity between faces of the plurality of persons; performs clothes recognition to generate clothes recognition scores relating to similarity between clothes of the plurality of persons; obtains inter-relational person scores relating to similarity between persons of the plurality of persons using the face recognition scores and the clothes recognition scores; and clusters the plurality of persons from the plurality of digital images using the inter-relational person scores to obtain clusters relating to identities of the persons from the plurality of persons.
摘要翻译：一种方法和装置处理数字图像。根据一个实施例的方法访问表示包括多个人的多个数字图像的数字数据; 执行面部识别以产生与所述多个人的面部之间的相似性相关的面部识别分数; 执行衣服识别以产生与多个人的衣服之间的相似性相关的衣服识别分数; 使用所述面部识别分数和所述衣服识别分数获得与所述多个人的人之间的相似性相关的关系人分数; 并且使用所述关联人员分数从所述多个数字图像中聚集所述多个人，以获得与来自所述多个人的人的身份有关的群集。

10. 发明申请

US20070086675A1 Segmenting images and simulating motion blur using an image sequence 有权
标题翻译：使用图像序列分割图像和模拟运动模糊
公开(公告)号：US20070086675A1
公开(公告)日：2007-04-19
申请号：US11248175
申请日：2005-10-13
申请人： Troy Chinen , Sergey Ioffe , Thomas Leung , Yang Song
发明人： Troy Chinen , Sergey Ioffe , Thomas Leung , Yang Song
IPC分类号： G06K9/36 , G06K9/20
CPC分类号： G06T5/002 , G06T7/11 , G06T7/194 , G06T7/215 , G06T11/00 , G06T2207/10016 , G06T2207/20036 , H04N5/2625
摘要： A sequence of images depicts a foreground object in motion. A base image is selected, and the other images in the sequence are co-registered with the base image in order to align the images to a common coordinate system. A background image and a binary foreground mask are generated from the sequence of aligned images. By applying the foreground mask to a chosen one of the aligned images, a representation of the moving object is extracted. After blurring the background image, the extracted representation may be superimposed onto the blurred background image to produce a new image.
摘要翻译：图像序列描绘了运动中的前景物体。选择基本图像，并且序列中的其他图像与基本图像共同对准，以便将图像对准到公共坐标系。从对齐图像的序列生成背景图像和二进制前景蒙版。通过将前景蒙版应用于所选择的一个对准的图像，提取移动物体的表示。在模糊背景图像之后，提取的表示可以叠加到模糊背景图像上以产生新图像。

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