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

US20180268537A1 Linear Grouping of Recognized Items in an Image 审中-公开
公开(公告)号：US20180268537A1
公开(公告)日：2018-09-20
申请号：US15988720
申请日：2018-05-24
申请人： Michael J. Gormish , Edward Schwartz
发明人： Michael J. Gormish , Edward Schwartz
IPC分类号： G06T7/00 , G06K9/62 , G06T7/70 , G06K9/52 , G06T7/73 , G06T7/60
CPC分类号： G06T7/0004 , G06K9/32 , G06K9/52 , G06K9/6215 , G06K9/6218 , G06K9/6267 , G06T7/30 , G06T7/60 , G06T7/70 , G06T7/73 , G06T2207/30108
摘要： A system and method that determines multiple linear groups of horizontally placed items in an image is disclosed. The method includes receiving an image including a portion of a shelving unit, identifying a plurality of items in the image, determining a plurality of facings, clustering the plurality of facings, merging a plurality of clusters and determining a list of linear groups in the image.

2. 发明授权

US09904990B2 Single image rectification 有权
公开(公告)号：US09904990B2
公开(公告)日：2018-02-27
申请号：US14975644
申请日：2015-12-18
申请人： Jorge Moraleda , Ekta Prashnani , Michael J. Gormish , Kathrin Berkner , Silvio Savarese
发明人： Jorge Moraleda , Ekta Prashnani , Michael J. Gormish , Kathrin Berkner , Silvio Savarese
IPC分类号： G06K9/00 , G06T5/00 , G06T5/10 , G06K9/32 , G06T3/00
CPC分类号： G06T5/006 , G06K9/3233 , G06K9/3275 , G06K2009/2045 , G06T3/00 , G06T3/0006 , G06T5/10 , G06T7/62 , G06T2207/10012 , G06T2207/10028 , G06T2207/20048 , G06T2207/20061 , G06T2207/20212
摘要： The disclosure includes a system and method for performing image rectification using a single image and information identified from the single image. An image recognition application receives an input image, identifies a plurality of objects in the input image, estimates rectification parameters for the plurality of objects, identifies a plurality of candidate rectification parameters using a voting procedure on the rectification parameters for the plurality of objects, estimates final rectification parameters based on the plurality of candidate rectification parameters, computes a global transformation matrix using the final rectification parameters, and performs image rectification on the input image using the global transformation matrix.

3. 发明授权

US09619899B2 Distinguishing between stock keeping units using hough voting methodology 有权
公开(公告)号：US09619899B2
公开(公告)日：2017-04-11
申请号：US14582046
申请日：2014-12-23
申请人： Bharathi Shekar , Sri Kaushik Pavani , Anshul Garg , Michael J. Gormish
发明人： Bharathi Shekar , Sri Kaushik Pavani , Anshul Garg , Michael J. Gormish
IPC分类号： G06T7/60 , G06T7/00 , G06K9/62 , G06Q10/08 , G06K9/00
CPC分类号： G06T7/11 , G06K9/00771 , G06K9/6215 , G06K9/6292 , G06Q10/087 , G06T7/62
摘要： The disclosure includes a system and method for distinguishing between items of similar appearance that vary in size. An image recognition application receives an image including a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, determines a dimension of the region of interest for each identified item in pixels, determines a plurality of pixel-to-physical dimension ratios for each identified item, identifies a selected pixel-to-physical dimension ratio among the plurality of pixel-to-physical dimension ratios, and determines a stock keeping unit identifier of each identified item in the image based on the selected pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.

4. 发明申请

US20160180549A1 Distinguishing Between Stock Keeping Units Using Hough Voting Methodology 有权
标题翻译：使用霍普表决方法区分库存单位
公开(公告)号：US20160180549A1
公开(公告)日：2016-06-23
申请号：US14582046
申请日：2014-12-23
申请人： Bharathi Shekar , Sri Kaushik Pavani , Anshul Garg , Michael J. Gormish
发明人： Bharathi Shekar , Sri Kaushik Pavani , Anshul Garg , Michael J. Gormish
IPC分类号： G06T7/60 , G06T7/00 , G06Q10/08 , G06K9/62
CPC分类号： G06T7/11 , G06K9/00771 , G06K9/6215 , G06K9/6292 , G06Q10/087 , G06T7/62
摘要： The disclosure includes a system and method for distinguishing between items of similar appearance that vary in size. An image recognition application receives an image including a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, determines a dimension of the region of interest for each identified item in pixels, determines a plurality of pixel-to-physical dimension ratios for each identified item, identifies a selected pixel-to-physical dimension ratio among the plurality of pixel-to-physical dimension ratios, and determines a stock keeping unit identifier of each identified item in the image based on the selected pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.
摘要翻译：本公开包括用于区分大小不同的类似外观的项目的系统和方法。图像识别应用接收包括多个项目的图像，识别图像中的每个项目，为图像中的每个识别的项目生成感兴趣的区域，以像素为单位确定每个识别的项目的感兴趣区域的维度，确定针对每个识别的项目的多个像素对物理维度比率，识别多个像素对物理维度比率之间的所选择的像素与物理维度比率，并确定图像中每个识别项目的库存单位标识符基于所选择的像素对物理维度比率和每个识别项目的感兴趣区域的维度。

5. 发明授权

US08838600B2 Method for determining constraint-based relationships between devices for interacting and sharing information 有权
标题翻译：用于确定用于交互和共享信息的设备之间基于约束的关系的方法
公开(公告)号：US08838600B2
公开(公告)日：2014-09-16
申请号：US13078839
申请日：2011-04-01
申请人： Andrea Mariotti , Berna Erol , Michael J. Gormish , Gregory J. Wolff
发明人： Andrea Mariotti , Berna Erol , Michael J. Gormish , Gregory J. Wolff
IPC分类号： G06F17/30 , H04W4/20 , H04W60/00
CPC分类号： H04W4/206 , H04W4/21 , H04W60/00
摘要： The system includes a registry server and devices. The registry server is coupled to the devices for publishing or registering spots, managing places and authenticating membership and places. The registry server includes a data store for constraint metadata, an authentication module, a spot manager module, a place manager module and a query response module. The devices are adapted to collect field values, create spots, access places, and interact and share information with other spots. In one embodiment, the devices include a constraint collection module, a spot creation module, a query module, a challenge creation module, a presentation module, a challenge response module, a spot action module and a spot communication module. The present invention includes methods for creating a spot, for generating and approving a challenge, for direct communication or sharing of documents, for performing an action based upon information space membership and for searching for available places.
摘要翻译：该系统包括注册表服务器和设备。注册服务器耦合到用于发布或注册点，管理场所和认证会员资格的设备。注册服务器包括用于约束元数据的数据存储，认证模块，现场管理器模块，场所管理器模块和查询响应模块。这些设备适用于收集现场值，创建点，访问场所，并与其他景点进行交互和共享信息。在一个实施例中，设备包括约束收集模块，点创建模块，查询模块，挑战创建模块，呈现模块，挑战响应模块，点动模块和点通信模块。本发明包括用于创建点的方法，用于生成和批准用于直接通信或共享文档的挑战，用于基于信息空间成员进行动作并搜索可用的地点。

6. 发明申请

US20140258331A1 Form Aggregation Based on Marks in Graphic Form Fields 有权
标题翻译：基于图形格式字段的表格汇总
公开(公告)号：US20140258331A1
公开(公告)日：2014-09-11
申请号：US13789605
申请日：2013-03-07
申请人： Edward L. Schwartz , John W. Barrus , Michael J. Gormish
发明人： Edward L. Schwartz , John W. Barrus , Michael J. Gormish
IPC分类号： G06F17/30
CPC分类号： G06F17/30392 , G06F17/30277
摘要： The disclosure includes a system and method for aggregating form data based on marks in graphic form fields. The system includes a controller, a request customization module, a search module and a presentation module. The controller receives data indicating an initiation of a search request from a user, data describing a form selected by the user, data describing a graphic form field specified by the user in the form and data describing a region of interest specified by the user in the graphic form field. The request customization module customizes the search request using the region of interest. The search module performs a form search on a collection of form data using the search request to determine one or more matching forms that each include at least one mark satisfying the region of interest. The presentation module provides the one or more matching forms to the user.
摘要翻译：本公开包括用于基于图形形式字段中的标记聚合表单数据的系统和方法。该系统包括控制器，请求定制模块，搜索模块和呈现模块。控制器从用户接收指示搜索请求的发起的数据，描述由用户选择的表单的数据，描述用户以表单指定的图形形式字段的数据和描述用户在图形格式字段。请求定制模块使用感兴趣的区域自定义搜索请求。搜索模块使用搜索请求对表单数据的集合执行表单搜索，以确定一个或多个匹配表单，每个匹配表单包括满足感兴趣区域的至少一个标记。呈现模块向用户提供一个或多个匹配表单。

7. 发明申请

US20120053992A1 TECHNIQUES FOR PRICING A TASK 审中-公开
标题翻译：定价任务的技术
公开(公告)号：US20120053992A1
公开(公告)日：2012-03-01
申请号：US12871720
申请日：2010-08-30
申请人： Berna Erol , Michael J. Gormish , Jorge Moraleda , Timothee Bailloeul , Xu Liu , David G. Stork
发明人： Berna Erol , Michael J. Gormish , Jorge Moraleda , Timothee Bailloeul , Xu Liu , David G. Stork
IPC分类号： G06Q10/00
CPC分类号： G06Q30/0206
摘要： Techniques for pricing a task are provided. The pricing may be based on attributes of the input information and one or more rules determined for the input information. The rules may be based on one or more variables and customer-specified constraints.
摘要翻译：提供了定价任务的技术。定价可以基于输入信息的属性和为输入信息确定的一个或多个规则。规则可以基于一个或多个变量和客户指定的约束。

8. 发明授权

US07792362B2 Reformatting documents using document analysis information 有权
标题翻译：使用文档分析信息重新格式化文档
公开(公告)号：US07792362B2
公开(公告)日：2010-09-07
申请号：US11893825
申请日：2007-08-16
申请人： Kathrin Berkner , Christophe Marle , Edward L. Schwartz , Michael J. Gormish
发明人： Kathrin Berkner , Christophe Marle , Edward L. Schwartz , Michael J. Gormish
IPC分类号： G06K9/34
CPC分类号： G06T11/60 , G06F17/30905
摘要： A method and apparatus for reformatting electronic documents is disclosed. In one embodiment, the method comprises performing layout analysis on an electronic version of a document to locate text zones, assigning attributes for scale and importance to text zones in the electronic version of the document, and reformatting text in the electronic version of the document based on the attributes to create an image.
摘要翻译：公开了一种重新格式化电子文件的方法和装置。在一个实施例中，该方法包括对文档的电子版本执行布局分析以定位文本区域，为文档的电子版本中的文本区域分配尺度和重要性的属性，以及重新格式化文档的电子版本中的文本关于创建图像的属性。

9. 发明授权

US07660473B2 Error concealment using icons for JPEG and JPEG 2000 compressed images 失效
标题翻译：错误隐藏使用JPEG和JPEG 2000压缩图像的图标
公开(公告)号：US07660473B2
公开(公告)日：2010-02-09
申请号：US10286115
申请日：2002-11-01
申请人： Michael J. Gormish
发明人： Michael J. Gormish
IPC分类号： G06K9/36
CPC分类号： H04N19/895
摘要： A method and apparatus for concealing errors using lower resolution images for compressed images is described. In one embodiment, the method comprises receiving a codestream data of an image and determining a location of an error region in coefficients using an icon.
摘要翻译：描述使用用于压缩图像的较低分辨率图像来隐藏错误的方法和装置。在一个实施例中，该方法包括接收图像的码流数据，并使用图标确定系数中的误差区域的位置。

10. 再颁专利

USRE40405E1 Method and apparatus for securing executable programs against copying 有权
标题翻译：用于保护可执行程序免于复制的方法和装置
公开(公告)号：USRE40405E1
公开(公告)日：2008-06-24
申请号：US09414994
申请日：1999-10-07
申请人： Edward L. Schwartz , Michael J. Gormish
发明人： Edward L. Schwartz , Michael J. Gormish
IPC分类号： H04L9/00
CPC分类号： G06F21/123 , G06F2221/2107
摘要： A secure system for executing program code in an insecure environment while making it impossible, or at least impractical, to determine how to copy the program code and associated data is provided. A program memory contains encrypted program data and security circuitry contained within an integrated circuit is provided for decrypting the program data as it is needed by a processor. A portion of the processing steps which would be done by the processor in an insecure system is performed in this secure system within the secure circuitry using portions of the decrypted program data which are not provided to the processor. Program data is parsed it out based on a proper request to the security chip from the processor. A key value stored in volatile memory is used in the decrypting process and the volatile memory is positioned on the integrated circuit such that its contents are lost before a chip peel provides access to the volatile memory.
摘要翻译：提供了一种用于在不安全环境中执行程序代码的安全系统，同时使得不可能或至少不切实际地确定如何复制程序代码和相关联的数据。程序存储器包含加密的程序数据，并且集成电路中包含的安全电路被提供用于对处理器需要的程序数据进行解密。在安全电路中的该安全系统中，使用未提供给处理器的解密程序数据的部分，在不安全系统中由处理器完成的处理步骤的一部分被执行。程序数据根据从处理器向安全芯片的适当请求进行解析。在解密处理中使用存储在易失性存储器中的键值，并且易失性存储器位于集成电路上，使得在芯片剥离提供对易失性存储器的访问之前其内容丢失。

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