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

WO2011152844A1 IMAGE CLUSTERING USING A PERSONAL CLOTHING MODEL 审中-公开
标题翻译：使用个人服装模型的图像聚类
公开(公告)号：WO2011152844A1
公开(公告)日：2011-12-08
申请号：PCT/US2010/044142
申请日：2010-08-02
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , ZHANG, Tong , ZHANG, Wei , TRETTER, Daniel
发明人： ZHANG, Tong , ZHANG, Wei , TRETTER, Daniel
IPC分类号： G06K9/46 , G06T7/40
CPC分类号： G06K9/6256 , G06K9/00677
摘要： The disclosure relates to a system and a method for generating clothing feature data representative of at least one clothing feature of a piece of clothing being worn by the person in a set of images, and training a discriminative clothing classifier using the clothing feature data to provide a personal clothing model that corresponds to the piece of clothing. The personal clothing model can be used to identify additional images in which the person appears.
摘要翻译：本公开涉及一种用于生成表示人在一组图像中穿着的服装的至少一个服装特征的服装特征数据的系统和方法，并且使用服装特征数据训练鉴别服装分类器以提供一件与服装相对应的个人服装模特。个人服装模型可以用于识别该人出现的其他图像。

2. 发明申请

WO2011152843A1 CLOTHING-BASED IMAGE CLUSTERING BASED ON CLUSTER ENSEMBLE SETS 审中-公开
标题翻译：基于集群组合的基于服装的图像聚类
公开(公告)号：WO2011152843A1
公开(公告)日：2011-12-08
申请号：PCT/US2010/044135
申请日：2010-08-02
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , ZHANG, Tong , ZHANG, Wei , TRETTER, Daniel
发明人： ZHANG, Tong , ZHANG, Wei , TRETTER, Daniel
IPC分类号： G06F17/00 , G06T1/00 , G06F13/14
CPC分类号： G06K9/6218 , G06K9/00677
摘要： The disclosure is related to a system and method for learning robust clothing clustering based on a cluster ensemble technique applied to the clothing features of images to improve clustering of images. Different types of clothing features that are complementary to each other are computed to provide extensive description of the clothing in the images. Multiple partitions are computed based on the clothing features to generate a cluster ensemble set. A consensus function is applied to the multiple partitions to generate a final clothing consensus clustering that encompasses the information contained in the multiple partitions. A system and method are disclosed for clustering images based on the clothing of one or more persons in the images.
摘要翻译：本公开涉及用于基于应用于图像的服装特征的群集合成技术来学习鲁棒服装聚类的系统和方法，以改善图像的聚类。计算出彼此互补的不同类型的服装功能，以便对图像中的服装进行广泛的描述。基于服装特征计算多个分区以生成群集集合集。将共同功能应用于多个分区以生成包含多个分区中包含的信息的最终服装共识聚类。公开了一种基于图像中的一个或多个人的衣服对图像进行聚类的系统和方法。

3. 发明申请

WO2011065952A1 FACE RECOGNITION APPARATUS AND METHODS 审中-公开
标题翻译：脸部识别装置和方法
公开(公告)号：WO2011065952A1
公开(公告)日：2011-06-03
申请号：PCT/US2009/066053
申请日：2009-11-30
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , ZHANG, Tong , ZHANG, Wei
发明人： ZHANG, Tong , ZHANG, Wei
IPC分类号： G06K9/00 , G06T7/40
CPC分类号： G06K9/6253 , G06K9/00221 , G06K9/6227
摘要： One or more facial recognition categories are assigned to a face region detected in an input image (24). Each of the facial recognition categories is associated with a respective set of one or more different feature extraction modules (66) and a respective set of one or more different facial recognition matching modules (76). For each of the facial recognition categories assigned to the face region, the input image (24) is processed with each of the feature extraction modules (66) associated with the facial recognition category to produce a respective facial region descriptor vector of facial region descriptor values characterizing the face region. A recognition result (96) between the face region and a reference face image (28) is determined based on application of the one or more facial recognition matching modules (76) associated with the facial recognition categories assigned to the face region to the facial region descriptor vectors produced for the face region detected in the input image (24).
摘要翻译：一个或多个面部识别类别被分配给在输入图像（24）中检测到的面部区域。每个面部识别类别与相应的一组一个或多个不同的特征提取模块（66）和相应的一组一个或多个不同的面部识别匹配模块（76）相关联。对于分配给面部区域的每个面部识别类别，与与面部识别类别相关联的每个特征提取模块（66）处理输入图像（24），以产生面部区域描述符值的相应面部区域描述符向量表征脸部区域。基于与分配给面部区域的面部识别类别相关联的一个或多个面部识别匹配模块（76）到面部区域的应用来确定面部区域和参考面部图像（28）之间的识别结果（96）为在输入图像（24）中检测到的面部区域产生的描述符向量。

4. 发明申请

WO2011037579A1 FACE RECOGNITION APPARATUS AND METHODS 审中-公开
标题翻译：脸部识别装置和方法
公开(公告)号：WO2011037579A1
公开(公告)日：2011-03-31
申请号：PCT/US2009/058476
申请日：2009-09-25
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , ZHANG, Wei , ZHANG, Tong
发明人： ZHANG, Wei , ZHANG, Tong
IPC分类号： G06K9/00 , G06T7/40
CPC分类号： G06K9/00281
摘要： Interest regions are detected in respective images (18) having face regions labeled with respective facial part labels. For each of the detected interest regions, a respective facial region descriptor vector of facial region descriptor values characterizing the detected interest region is determined. Ones of the facial part labels are assigned to respective ones of the facial region descriptor vectors. For each of the facial part labels, a respective facial part detector (20) that detects facial region descriptor vectors corresponding to the facial part label is built. The facial part detectors (20) are associated with rules (30) that qualify segmentation results of the facial part detectors (20) based on spatial relations between interest regions detected in images and the respective face part labels assigned to the facial part detectors (20). Faces in images are detected and recognized based on application of the facial part detectors (20) to images.
摘要翻译：在具有用相应的面部标签标记的面部区域的各个图像（18）中检测兴趣区域。对于每个检测到的感兴趣区域，确定表征检测到的兴趣区域的面部区域描述符值的相应面部区域描述符向量。面部部分标签的一部分被分配给面部区域描述符向量中的相应的一个。对于每个面部部分标签，构建检测与面部部分标签相对应的面部区域描述符向量的相应面部部分检测器（20）。面部部分检测器（20）与根据图像中检测到的兴趣区域和分配给面部部分检测器的相应面部部分标签（20）之间的空间关系来限定面部部分检测器（20）的分割结果的规则（30）相关联）。基于面部部件检测器（20）对图像的应用来检测和识别图像中的面部。

5. 发明申请

WO2011152821A1 CLUSTERING IMAGES 审中-公开
标题翻译：聚集图像
公开(公告)号：WO2011152821A1
公开(公告)日：2011-12-08
申请号：PCT/US2010/036899
申请日：2010-06-01
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , ZHANG, Wei , ZHANG, Tong , TRETTER, Daniel
发明人： ZHANG, Wei , ZHANG, Tong , TRETTER, Daniel
IPC分类号： G06T7/00
CPC分类号： G06K9/6267 , G06K9/00234 , G06K9/00362 , G06K9/00671
摘要： A method and system for clustering images, comprising detecting faces in respective images to generate face data, generating a first cluster of images using the face data, the first cluster comprising images with a common face and representing a corresponding person, generating a second cluster of images using clothes data representing a set of clothing signatures, the second cluster comprising images with a common set of clothes, and using the first and second clusters to link an image of the person to the clusters in order to generate a third cluster for the person.
摘要翻译：一种用于对图像进行聚类的方法和系统，包括检测各个图像中的面部以产生面部数据，使用面部数据产生第一图像簇，所述第一簇包括具有共同面部并且表示对应的人的图像，生成第二簇使用表示一组服装签名的衣服数据的图像，所述第二群集包括具有共同衣服的图像，以及使用所述第一和第二群集将所述人的图像链接到所述群集，以便为所述人生成第三群集。

6. 发明申请

WO2011153270A2 IMAGE RETRIEVAL 审中-公开
标题翻译：图像检索
公开(公告)号：WO2011153270A2
公开(公告)日：2011-12-08
申请号：PCT/US2011/038800
申请日：2011-06-01
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , ZHANG, Tong , WU, Peng
发明人： ZHANG, Tong , WU, Peng
IPC分类号： G06F17/30 , G06F3/14 , G06T7/00 , G06K9/46
CPC分类号： G06K9/00295 , G06F17/30247 , G06K9/00369 , G06K2009/00328 , H04N5/247
摘要： A method, comprising receiving query data including an image of a person, and detecting a face of the person in the image to create a detected face, generating face data and clothing data using the detected face including a measure of characteristics of the face and clothing of the person, and retrieving images and video for the person and a related group of people by comparing the face data and clothing data of the person with multiple measures for the characteristics of faces and clothing generated from a set of images and video in which other people appear wherein co-appearances of the person with at least some of the other people are used to retrieve content in which the person and people from the related group appear.
摘要翻译：一种方法，包括接收包括人的图像的查询数据，以及检测图像中的人的面部以创建检测到的面部，使用检测到的面部生成面部数据和服装数据，所述面部包括面部和衣服的特征的量度并且通过将人的面部数据和服装数据与从一组图像和视频产生的面部和衣服的特征的多个度量进行比较来检索人和相关人群的图像和视频，其中其他人们出现其中与至少一些其他人的人的共同出现被用于检索相关组中的人和人出现的内容。

7. 发明申请

WO2008033433A2 COMPUTATIONAL MUSIC-TEMPO ESTIMATION 审中-公开
标题翻译：计算音乐 - 速度估计
公开(公告)号：WO2008033433A2
公开(公告)日：2008-03-20
申请号：PCT/US2007/019876
申请日：2007-09-11
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY L.P. , CHANG, Yu-Yao , SAMADANI, Ramin , ZHANG, Tong , WIDDOWSON, Simon
发明人： CHANG, Yu-Yao , SAMADANI, Ramin , ZHANG, Tong , WIDDOWSON, Simon
CPC分类号： G10H1/40 , G10H2210/076
摘要： Various method and system embodiments of the present invention are directed to computational estimation of a tempo for a digitally encoded musical selection. In certain embodiments of the present invention, described below, a short portion of a musical selection is analyzed to determine the tempo of the musical selection. The digitally encoded musical selection sample is computationally transformed to produce a power spectrum corresponding to the sample, in turn transformed to produce a two-dimensional strength-of-onset matrix (618). The two-dimensional strength-of-onset matrix is then transformed (806) into a set of strength-of-onset/time functions (716) for each of a corresponding set of frequency bands (704-707). The strength-of-onset/time functions are then analyzed to find a most reliable onset interval (808, 8100) that is transformed into an estimated tempo returned by the analysis (812).
摘要翻译：本发明的各种方法和系统实施例涉及用于数字编码音乐剧选择的节奏的计算估计。在下面描述的本发明的某些实施例中，分析音乐选择的一小部分以确定音乐选择的节奏。对数字编码的音乐选择样本进行计算变换以产生对应于样本的功率谱，其又被变换以产生二维起始强度矩阵（618）。然后将二维起始强度矩阵变换（806）为对应的一组频带（704-707）中的每一个的一组起始强度/时间函数（716）。然后分析发作强度/时间函数以找到转换成由分析返回的估计节奏的最可靠的发作间隔（808,8100）（812）。

8. 发明申请

WO2009154589A3 PRINTING STRUCTURED DOCUMENTS 审中-公开
公开(公告)号：WO2009154589A3
公开(公告)日：2009-12-23
申请号：PCT/US2008/001438
申请日：2008-01-31
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY L.P. , XIAO, Jun , ATKINS, Clayton , ZHANG, Tong , LIU, Sam
发明人： XIAO, Jun , ATKINS, Clayton , ZHANG, Tong , LIU, Sam
IPC分类号： G06F3/12 , G06F3/048
摘要： Print objects (38) are captured. In the process of capturing each of the print objects (38) a user input gesture (34) over a region of a document (18) being rendered on a display (16) in accordance with a structured object specification (20) of the document (18) is received; an element of the structured object specification (20) being rendered within an active area of the user input gesture (34) on the display (16) is identified; the user input gesture (34) is interpreted as a print content designation command; and the print object (38) is derived from the structured object specification (20) in accordance with the identified element of the structured object specification (20) and the print content designation command. A print layout (32) of the print objects (38) on one or more pages (50) is determined. The print layout (32) is outputted.

9. 发明申请

WO2008088883A1 WEB-BASED VIDEO BROWSING 审中-公开
标题翻译：基于WEB的视频浏览
公开(公告)号：WO2008088883A1
公开(公告)日：2008-07-24
申请号：PCT/US2008/000697
申请日：2008-01-18
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY L.P. , ZHANG, Tong , WU, Peng , LIU, Sam
发明人： ZHANG, Tong , WU, Peng , LIU, Sam
IPC分类号： H04N7/173 , G06F17/30
CPC分类号： G06F17/30274 , G06F17/30852 , G06F17/30899 , H04N21/2387 , H04N21/6587
摘要： A system for web-based video browsing includes a web server (10) and a web client (12). The web server (10) and the web client (12) cooperatively provide a set of video browsing functions (18). The video browsing functions (18) enable a user of the web client (12) to browse a source video (22) and select a video frame (30) from the source video (22). The distribution of the video browsing functions (18) between the web server (10) and the web client (12) may be adapted to a communication speed between the web server (10) and the web client (12).
摘要翻译：用于基于web的视频浏览的系统包括web服务器（10）和web客户机（12）。网络服务器（10）和网络客户端（12）协作地提供一组视频浏览功能（18）。视频浏览功能（18）使得网络客户端（12）的用户能够浏览源视频（22）并从源视频（22）中选择视频帧（30）。 web服务器（10）和web客户端（12）之间的视频浏览功能（18）的分布可以适应于web服务器（10）和web客户端（12）之间的通信速度。

10. 发明申请

WO2006019573A1 ECG ELECTRODE CHARACTERIZATION AND COMPENSATION 审中-公开
标题翻译：心电图电极特征和补偿
公开(公告)号：WO2006019573A1
公开(公告)日：2006-02-23
申请号：PCT/US2005/023930
申请日：2005-07-06
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , BLAKLEY, Daniel Robert , ZHANG, Tong , SIMSKE, Steven John
发明人： BLAKLEY, Daniel Robert , ZHANG, Tong , SIMSKE, Steven John
IPC分类号： A61B5/0424
CPC分类号： A61B5/0428 , A61B5/0424
摘要： Systems, methodologies, media, and other embodiments associated with electrocardiogram electrode characterization and compensation are described. One exemplary system embodiment 100 includes a characterization logic 110 configured to generate signals designed to facilitate characterizing an electrocardiogram electrode 120. The characterization logic 110 may also be configured to analyze signals produced in response to introducing the signals into a subject 125. The example system 100 may also include a compensation logic 140 configured to determine whether an electrode is performing in a desired manner and to selectively compensate for electrode performance.
摘要翻译：描述了与心电图电极表征和补偿相关联的系统，方法，介质和其它实施例。一个示例性系统实施例100包括表征逻辑110，其被配置为产生被设计为有助于表征心电图电极120的信号。表征逻辑110还可以被配置为分析响应于将信号引入到对象125中而产生的信号。示例系统100 还可以包括补偿逻辑140，其被配置为确定电极是否以期望的方式执行并且选择性地补偿电极性能。

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