专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明授权

US07227976B1 Method and system for real-time facial image enhancement 有权
标题翻译：用于实时面部图像增强的方法和系统
公开(公告)号：US07227976B1
公开(公告)日：2007-06-05
申请号：US10609245
申请日：2003-06-27
申请人： Namsoon Jung , Rajeev Sharma
发明人： Namsoon Jung , Rajeev Sharma
IPC分类号： G06K9/00 , G06T15/00 , A61B3/10
CPC分类号： G06T11/00 , G06K9/00228 , G06T7/20
摘要： The present invention is a system and method for detecting facial features of humans in a continuous video and superimposing virtual objects onto the features automatically and dynamically in real-time. The suggested system is named Facial Enhancement Technology (FET). The FET system consists of three major modules, initialization module, facial feature detection module, and superimposition module. Each module requires demanding processing time and resources by nature, but the FET system integrates these modules in such a way that real time processing is possible. The users can interact with the system and select the objects on the screen. The superimposed image moves along with the user's random motion dynamically. The FET system enables the user to experience something that was not possible before by augmenting the person's facial images. The hardware of the FET system comprises the continuous image-capturing device, image processing and controlling system, and output display system.
摘要翻译：本发明是用于在连续视频中检测人的面部特征并且将虚拟对象实时地自动和动态地叠加到特征上的系统和方法。建议的系统称为面部增强技术（FET）。 FET系统由三个主要模块，初始化模块，面部特征检测模块和叠加模块组成。每个模块本质上都需要苛刻的处理时间和资源，但FET系统可以以实时处理的方式集成这些模块。用户可以与系统进行交互，并在屏幕上选择对象。叠加的图像随着用户的随机运动动态移动。 FET系统使用户能够通过增强人脸部图像来体验以前不可能的东西。 FET系统的硬件包括连续的图像捕获设备，图像处理和控制系统以及输出显示系统。

62. 发明授权

US10354262B1 Brand-switching analysis using longitudinal tracking of at-shelf shopper behavior 有权
公开(公告)号：US10354262B1
公开(公告)日：2019-07-16
申请号：US15171873
申请日：2016-06-02
申请人： Jeff Hershey , Rajeev Sharma , Richard Hirata , Krishna Botla
发明人： Jeff Hershey , Rajeev Sharma , Richard Hirata , Krishna Botla
IPC分类号： G06Q10/00 , G06Q30/02 , H04L29/08
摘要： A method and system for analyzing shopper switching behavior over multiple shopping trips. Specifically, shopper behavior can be analyzed to generate a shopper behavior profile. Aggregating profile data across many shopping trips over time can then be used to generate analytics regarding the shopper's behavior regarding switching between products or brands and whether the shopper's purchase decisions occurred at-shelf or pre-shelf. Further, the data can be aggregated across many shoppers The analysis can then be used to make recommendations to manufacturers or retailers about how to influence shoppers to switch to a brand from a competitor, or to prevent a shopper from switching to a competitor. A deployment of cameras and mobile signal sensors can be utilized to recognize shoppers and track their behavior. Demographics information can also be estimated about the tracked shoppers. The visual and mobile signal trajectories can be fused to form a single shopper trajectory, then associated with Point of Sale (PoS) data. This results in a dataset describing the shopping trip for each tracked shopper.

63. 发明申请

US20130125200A1 Method of securing data in 2D bar codes using SSL 有权
标题翻译：使用SSL保护2D条形码数据的方法
公开(公告)号：US20130125200A1
公开(公告)日：2013-05-16
申请号：US13294548
申请日：2011-11-11
申请人： Rajeev Sharma
发明人： Rajeev Sharma
IPC分类号： H04L9/32 , G06F21/00
CPC分类号： G06F21/36 , G06F21/64 , H04L9/3226 , H04L63/0823 , H04L63/123
摘要： Methods and apparatus authenticate a printed document associated with a source entity. The printed document includes a two-dimensional code (2-D code) that includes data encoded therein. The encoded data includes a resource locator to an intent. An image of the 2-D code is decoded to obtain the resource locator to an intent, and it is detected whether the resource locator to an intent includes a protocol identifier designating a secure 2-D code. If so, the protocol identifier is replaced with a protocol identifier used to access a secure server of the source entity located at a host portion of the resource locator. The secure server is accessed to obtain the intent. A certificate of the secure server is accessed and an electronic device displays an indicator of whether the certificate is valid and also displays the intent. The indicator may be used to decide whether the intent can be trusted.
摘要翻译：方法和设备认证与源实体相关联的打印文档。打印文档包括包含其中编码的数据的二维码（2-D码）。编码数据包括一个意图的资源定位符。解码2-D码的图像以获得资源定位符的意图，并且检测资源定位符是否包含指定安全2-D码的协议标识符。如果是，协议标识符被替换为用于访问位于资源定位符的主机部分的源实体的安全服务器的协议标识符。访问安全服务器以获取意图。访问安全服务器的证书，电子设备显示证书是否有效的指示符，并显示意图。该指标可用于决定意图是否可信。

64. 发明申请

US20120248760A1 CONNECTING BLOCK 有权
标题翻译：连接块
公开(公告)号：US20120248760A1
公开(公告)日：2012-10-04
申请号：US13076752
申请日：2011-03-31
申请人： Rajeev Sharma
发明人： Rajeev Sharma
IPC分类号： F16L27/00
CPC分类号： F16L39/00 , F16L41/086 , F16L58/188
摘要： A connecting block includes a first member having a flow header extending from a sealing surface, a planar end face oppositely directed with respect to the sealing surface, and a perimeter wall angularly oriented with respect to the sealing surface. A second member is slidably received within the perimeter wall of the first member and has a flow member receiving bore axially aligned with the flow header. A bonding zone is created by heating both the first and second members until the planar end face and the planar interior face join together to create a physical connection between the first and second members. A material of the second member is corrosively sacrificial with respect to a material of the first member.
摘要翻译：连接块包括具有从密封表面延伸的流动集管的第一构件，相对于密封表面相对定向的平面端面和相对于密封表面成角度定向的周边壁。第二构件可滑动地容纳在第一构件的周边壁内，并且具有流动构件，其接收与流动集管轴向对齐的孔。通过加热第一和第二构件直到平面端面和平面内表面连接在一起以在第一和第二构件之间形成物理连接来产生粘结区。第二构件的材料相对于第一构件的材料是腐蚀性牺牲的。

65. 发明授权

US07505621B1 Demographic classification using image components 失效
标题翻译：使用图像分量进行人口统计分类
公开(公告)号：US07505621B1
公开(公告)日：2009-03-17
申请号：US10972316
申请日：2004-10-22
申请人： Pyush Agrawal , Rajeev Sharma
发明人： Pyush Agrawal , Rajeev Sharma
IPC分类号： G06K9/62 , G06K9/46 , G06K9/68
CPC分类号： G06K9/00288 , G06K9/6288 , G06K2009/00322
摘要： The present invention includes a system and method for automatically extracting the demographic information from images. The system detects the face in an image, locates different components, extracts component features, and then classifies the components to identify the age, gender, or ethnicity of the person(s) in the image. Using components for demographic classification gives better results as compared to currently known techniques. Moreover, the described system and technique can be used to extract demographic information in more robust manner than currently known methods, in environments where high degree of variability in size, shape, color, texture, pose, and occlusion exists. This invention also performs classifier fusion using Data Level fusion and Multi-level classification for fusing results of various component demographic classifiers. Besides use as an automated data collection system wherein given the necessary facial information as the data, the demographic category of the person is determined automatically, the system could also be used for targeting of the advertisements, surveillance, human computer interaction, security enhancements, immersive computer games and improving user interfaces based on demographic information.
摘要翻译：本发明包括一种用于从图像中自动提取人口统计信息的系统和方法。系统检测图像中的脸部，定位不同的部件，提取组件特征，然后对组件进行分类，以识别图像中的人的年龄，性别或种族。与目前已知的技术相比，使用组件进行人口统计分类可获得更好的结果。此外，在存在大小，形状，颜色，纹理，姿势和遮挡的高度变异性的环境中，所描述的系统和技术可以用于以比当前已知的方法更鲁棒的方式提取人口统计信息。本发明还使用数据级融合和多级分类进行分类器融合，用于融合各种组分人口统计分类器的结果。除了作为自动数据收集系统使用，其中给定必要的面部信息作为数据，人的人口统计类别被自动确定，该系统还可以用于广告，监视，人机交互，安全增强，沉浸式电脑游戏，并根据人口信息改善用户界面。

66. 发明授权

US07321854B2 Prosody based audio/visual co-analysis for co-verbal gesture recognition 失效
标题翻译：基于韵律的音视频共同分析协同语言手势识别
公开(公告)号：US07321854B2
公开(公告)日：2008-01-22
申请号：US10666460
申请日：2003-09-19
申请人： Rajeev Sharma , Mohammed Yeasin , Sanshzar Kettebekov
发明人： Rajeev Sharma , Mohammed Yeasin , Sanshzar Kettebekov
IPC分类号： G10L15/00
CPC分类号： G06K9/00335 , G10L15/24
摘要： The present method incorporates audio and visual cues from human gesticulation for automatic recognition. The methodology articulates a framework for co-analyzing gestures and prosodic elements of a person's speech. The methodology can be applied to a wide range of algorithms involving analysis of gesticulating individuals. The examples of interactive technology applications can range from information kiosks to personal computers. The video analysis of human activity provides a basis for the development of automated surveillance technologies in public places such as airports, shopping malls, and sporting events.
摘要翻译：本方法结合了来自人类手势的音频和视觉线索，用于自动识别。该方法阐述了一个人的言论的手势和韵律元素的共同分析框架。该方法可以应用于涉及分析个体的各种算法。互动技术应用的例子可以从信息亭到个人电脑。人类活动的视频分析为机场，商场和体育赛事等公共场所的自动化监控技术的开发奠定了基础。

67. 发明授权

US10963893B1 Personalized decision tree based on in-store behavior analysis 有权
公开(公告)号：US10963893B1
公开(公告)日：2021-03-30
申请号：US15051629
申请日：2016-02-23
申请人： Rajeev Sharma
发明人： Rajeev Sharma
IPC分类号： G06Q30/00 , G06Q30/02 , G06K9/00
摘要： A method and system for determining the hierarchical purchase decision process of a shopper in front of a product category in a retail store. Shopping consideration and the decision path the shopper can be obtained by combining behavior data with the category layout and transaction data. The hierarchical decision process can be determined based on observed actual in-store purchase behavior using a set of video cameras and processor implemented instructions for extracting the sequence and timing of the shopper's decision process. The hierarchical decision process, obtained by the clustering of shopper behavior data over multiple shopping trips, can not only identify the sequence of the decision, but can also quantify the volume of shopping trips at each level in the decision process and the amount of time spent by the shopper for making each decision. The decisions of the shopper for each product group can be captured down to the product attribute level. Such in-depth understanding can provide a picture of the relative importance of each product attribute in the purchase decision process, and can help retailers personalize targeted messaging to the shopper.

68. 发明授权

US08407509B2 Method for compensating for variations in data timing 有权
标题翻译：补偿数据时序变化的方法
公开(公告)号：US08407509B2
公开(公告)日：2013-03-26
申请号：US12901579
申请日：2010-10-11
申请人： Rajeev Sharma , Ajay Kumar , Naresh Dhamija , Atul Gupta , Ajay K. Gaite , Llamparidhi l
发明人： Rajeev Sharma , Ajay Kumar , Naresh Dhamija , Atul Gupta , Ajay K. Gaite , Llamparidhi l
IPC分类号： G06F1/04 , G06F13/00 , G06F13/42
CPC分类号： G06F13/1689 , G06F13/4243
摘要： A method for compensating for variations in timing of data sent to a processor on data bit lines relative to a strobe clock sent to the processor on a strobe clock line that can be used in a dual data rate (DDR) memory identifies discrete minimum and maximum time offset values for test data in selected data bit patterns for the data bit lines. The discrete minimum time offset value is the minimum timing adjustment required to allow the processor to receive the data in a steady-state condition during a data valid window of the strobe clock and the discrete maximum time offset value is a maximum timing adjustment required to allow the processor to receive the data in a steady-state condition during a data valid window of the strobe clock. The discrete minimum and maximum time offset values identify a valid range when the data bit lines supply data in a steady-state condition for latching into the processor by the strobe clock.
摘要翻译：用于补偿在数据位线上相对于在双数据速率（DDR）存储器中使用的选通时钟线上发送到处理器的选通时钟的数据位线发送的数据的时序变化的方法，该方法能够识别离散的最小和最大值用于数据位线的选定数据位模式中的测试数据的时间偏移值。离散的最小时间偏移值是在选通时钟的数据有效窗口期间允许处理器在稳态条件下接收数据所需的最小定时调整，并且离散最大时间偏移值是允许允许的最大定时调整所述处理器在所述选通时钟的数据有效窗口期间以稳态条件接收所述数据。当数据位线在稳态条件下提供数据以通过选通时钟锁存到处理器中时，离散的最小和最大时间偏移值标识有效范围。

69. 发明授权

US08145910B1 System and method to enforce collaboration rules for timestamps of a collaboration event 有权
标题翻译：执行协作事件时间戳的协作规则的系统和方法
公开(公告)号：US08145910B1
公开(公告)日：2012-03-27
申请号：US12040347
申请日：2008-02-29
申请人： Yash Kumar Gupta , Rajeev Sharma , Narinder Beri
发明人： Yash Kumar Gupta , Rajeev Sharma , Narinder Beri
IPC分类号： H04L9/32
CPC分类号： G06Q10/0633 , G06Q10/10 , H04L69/28
摘要： A method to enforce collaboration rules, in one example embodiment, comprises receiving a request to report a collaboration event to a collaboration workflow, receiving a reported time of the collaboration event, determining an origin of the reported time, updating the reported time with a central time service time when the origin of the reported time is not a central time service, and based on the updated reported time, selectively reporting the collaboration event into the collaboration workflow.
摘要翻译：在一个示例性实施例中，强制协作规则的方法包括：接收向协作工作流报告协作事件的请求，接收所述协作事件的报告时间，确定报告时间的来源，用中心更新报告的时间报告时间的来源不是中央时间服务的时间服务时间，并且基于更新的报告时间，选择性地将协作事件报告到协作工作流程中。

70. 发明授权

US07926854B2 Pipe joint block for fluid transfer 有权
标题翻译：用于流体输送的管接头块
公开(公告)号：US07926854B2
公开(公告)日：2011-04-19
申请号：US12249373
申请日：2008-10-10
申请人： Rajeev Sharma
发明人： Rajeev Sharma
IPC分类号： F16L41/00
CPC分类号： F28F9/0253
摘要： A connection block employs a support block with two parallel through holes that pass through parallel first and second flat block surfaces. First and second insert pipes have elongate portions and flanges. The elongate portions press-fit into the connection block and the flanges, not at pipe ends, abut against the first flat surface of the connection block when the pipes are installed. Upon installation, the ends the elongate portions of the pipes are formed into a flange by flattening the end against the second connection block surface. The junctures of the elongate portions and the first flanges form a flange radius that contacts a radius of the support block when the pipes are installed into the block. The elongate portions residing within the first and second through holes make a full contact fit against the inside diameters of the through holes. The flanges are perpendicular to the elongate portions.
摘要翻译：连接块采用具有穿过平行的第一和第二平坦块表面的两个平行通孔的支撑块。第一和第二插入管具有细长部分和凸缘。当安装管道时，细长部分压配合到连接块中，而不是在管端处的凸缘抵靠连接块的第一平坦表面。在安装时，通过将端部压平在第二连接块表面上，管的细长部分的端部形成为凸缘。细长部分和第一凸缘的接合处形成一个凸缘半径，当管子被安装到块体中时，其接触支撑块的半径。驻留在第一和第二通孔内的细长部分与通孔的内径形成完全接触配合。凸缘垂直于细长部分。

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