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

US20110128288A1 Region of Interest Selector for Visual Queries 审中-公开
标题翻译：视觉查询的兴趣区域选择器
公开(公告)号：US20110128288A1
公开(公告)日：2011-06-02
申请号：US12853188
申请日：2010-08-09
申请人： David Petrou , Zak Cohen , Pin Ting , Dar-Shyang Lee
发明人： David Petrou , Zak Cohen , Pin Ting , Dar-Shyang Lee
IPC分类号： G06T3/40
CPC分类号： G06K9/00664 , G06F16/434 , G06F16/438 , G06F16/532 , G06K9/2081
摘要： A client system receives an image such as a photograph, a screen shot, a scanned image, or a video frame. The image has a first resolution which is likely larger than a maximum resolution for visual queries. As such, if a visual query were created from the image some resolution would be lost. Instead, a user selects a region of interest within the image. The region of interest has a second resolution, which is smaller than the first resolution. The client system then creates a visual query from the region of interest. The visual query has a resolution no larger than a pre-defined maximum resolution for visual queries. Because the visual query is created from the region of interest rather, than the entire received image, most of the resolution is concentrated specifically on the region of interest. The visual query is then sent to a server system.
摘要翻译：客户端系统接收诸如照片，屏幕截图，扫描图像或视频帧的图像。该图像具有可能大于视觉查询的最大分辨率的第一分辨率。因此，如果从图像创建视觉查询，某些分辨率将会丢失。相反，用户选择图像内的感兴趣区域。感兴趣的区域有第二个分辨率，小于第一个分辨率。然后，客户端系统从感兴趣的区域创建一个视觉查询。视觉查询的分辨率不大于视觉查询的预定义最大分辨率。因为视觉查询是从感兴趣的区域创建的，而不是整个收到的图像，大部分的分辨率都集中在感兴趣的区域上。然后将视觉查询发送到服务器系统。

2. 发明授权

US08515185B2 On-screen guideline-based selective text recognition 有权
标题翻译：基于屏幕指南的选择性文本识别
公开(公告)号：US08515185B2
公开(公告)日：2013-08-20
申请号：US12626520
申请日：2009-11-25
申请人： Dar-Shyang Lee , Lee-Feng Chien , Aries Hsieh , Pin Ting , Kin Wong
发明人： Dar-Shyang Lee , Lee-Feng Chien , Aries Hsieh , Pin Ting , Kin Wong
IPC分类号： G06K9/72 , G06K9/46 , G06K9/66 , G06K9/20
CPC分类号： H04N5/23212 , G06K9/036 , G06K9/2081 , G06K9/228 , G06K9/325 , G06K2209/01 , H04N5/232 , H04N5/23248 , H04N5/23258 , H04N5/23264
摘要： A live video stream captured by an on-device camera is displayed on a screen with an overlaid guideline. Video frames of the live video stream are analyzed for a video frame with acceptable quality. A text region is identified in the video frame approximate to the on-screen guideline and cropped from the video frame. The cropped image is transmitted to an optical character recognition (OCR) engine, which processes the cropped image and generates text in an editable symbolic form (the OCR'ed text). A confidence score is determined for the OCR'ed text and compared with a threshold value. If the confidence score exceeds the threshold value, the OCR'ed text is outputted.
摘要翻译：由设备上相机拍摄的实时视频流将显示在具有重叠指南的屏幕上。分析实时视频流的视频帧，以获得可接受的质量的视频帧。在视频帧中识别文本区域，其近似于屏幕上的指南并从视频帧中裁剪。裁剪的图像被传输到光学字符识别（OCR）引擎，其处理裁剪的图像并以可编辑的符号形式（OCR的文本）生成文本。确定OCR文本的置信度，并与阈值进行比较。如果置信度分数超过阈值，则输出OCR的文本。

3. 发明申请

US20110123115A1 On-Screen Guideline-Based Selective Text Recognition 有权
标题翻译：基于屏幕指导的选择性文本识别
公开(公告)号：US20110123115A1
公开(公告)日：2011-05-26
申请号：US12626520
申请日：2009-11-25
申请人： Dar-Shyang Lee , Lee-Feng Chien , Aries Hsieh , Pin Ting , Kin Wong
发明人： Dar-Shyang Lee , Lee-Feng Chien , Aries Hsieh , Pin Ting , Kin Wong
IPC分类号： G06K9/18 , G06K9/72 , H04N5/225 , G09G5/02
CPC分类号： H04N5/23212 , G06K9/036 , G06K9/2081 , G06K9/228 , G06K9/325 , G06K2209/01 , H04N5/232 , H04N5/23248 , H04N5/23258 , H04N5/23264
摘要： A live video stream captured by an on-device camera is displayed on a screen with an overlaid guideline. Video frames of the live video stream are analyzed for a video frame with acceptable quality. A text region is identified in the video frame approximate to the on-screen guideline and cropped from the video frame. The cropped image is transmitted to an optical character recognition (OCR) engine, which processes the cropped image and generates text in an editable symbolic form (the OCR'ed text). A confidence score is determined for the OCR'ed text and compared with a threshold value. If the confidence score exceeds the threshold value, the OCR'ed text is outputted.
摘要翻译：由设备上相机拍摄的实时视频流将显示在具有重叠指南的屏幕上。分析实时视频流的视频帧，以获得可接受的质量的视频帧。在视频帧中识别文本区域，其近似于屏幕上的指南并从视频帧中裁剪。裁剪的图像被传输到光学字符识别（OCR）引擎，其处理裁剪的图像并以可编辑的符号形式（OCR的文本）生成文本。确定OCR文本的置信度，并与阈值进行比较。如果置信度分数超过阈值，则输出OCR的文本。

4. 发明申请

US20110081083A1 GESTURE-BASED SELECTIVE TEXT RECOGNITION 有权
标题翻译：基于GESTURE的选择性文本识别
公开(公告)号：US20110081083A1
公开(公告)日：2011-04-07
申请号：US12575015
申请日：2009-10-07
申请人： Dar-Shyang Lee , Lee-Feng Chien , Aries Hsieh , Pin Ting , Kin Wong
发明人： Dar-Shyang Lee , Lee-Feng Chien , Aries Hsieh , Pin Ting , Kin Wong
IPC分类号： G06K9/18
CPC分类号： G06K9/18 , G06K9/2081 , G06K2209/01
摘要： An image is displayed on a touch screen. A user's underline gesture on the displayed image is detected. The area of the image touched by the underline gesture and a surrounding region approximate to the touched area are identified. Skew for text in the surrounding region is determined and compensated. A text region including the text is identified in the surrounding region and cropped from the image. The cropped image is transmitted to an optical character recognition (OCR) engine, which processes the cropped image and returns OCR'ed text. The OCR'ed text is outputted.
摘要翻译：图像显示在触摸屏上。检测到用户在显示图像上的下划线手势。识别由下划线手势触摸的图像的区域和接近触摸区域的周边区域。确定并补偿周边地区的文字偏差。在周围区域中识别包括文本的文本区域，并从图像中裁剪。裁剪的图像被传输到光学字符识别（OCR）引擎，其处理裁剪的图像并返回OCR的文本。输出OCR的文本。

5. 发明授权

US08520983B2 Gesture-based selective text recognition 有权
标题翻译：基于手势的选择性文本识别
公开(公告)号：US08520983B2
公开(公告)日：2013-08-27
申请号：US12575015
申请日：2009-10-07
申请人： Dar-Shyang Lee , Lee-Feng Chien , Pin Ting , Aries Hsieh , Kin Wong
发明人： Dar-Shyang Lee , Lee-Feng Chien , Pin Ting , Aries Hsieh , Kin Wong
IPC分类号： G06K7/00 , G06K9/32
CPC分类号： G06K9/18 , G06K9/2081 , G06K2209/01
摘要： An image is displayed on a touch screen. A user's underline gesture on the displayed image is detected. The area of the image touched by the underline gesture and a surrounding region approximate to the touched area are identified. Skew for text in the surrounding region is determined and compensated. A text region including the text is identified in the surrounding region and cropped from the image. The cropped image is transmitted to an optical character recognition (OCR) engine, which processes the cropped image and returns OCR'ed text. The OCR'ed text is outputted.
摘要翻译：图像显示在触摸屏上。检测到用户在显示图像上的下划线手势。识别由下划线手势触摸的图像的区域和接近触摸区域的周边区域。确定并补偿周边地区的文字偏差。在周围区域中识别包括文本的文本区域，并从图像中裁剪。裁剪的图像被传输到光学字符识别（OCR）引擎，其处理裁剪的图像并返回OCR的文本。输出OCR的文本。

6. 发明授权

US08373905B2 Semantic classification and enhancement processing of images for printing applications 有权
公开(公告)号：US08373905B2
公开(公告)日：2013-02-12
申请号：US12334303
申请日：2008-12-12
申请人： Berna Erol , Jonathan J. Hull , Dar-Shyang Lee , Gregory J. Wolff
发明人： Berna Erol , Jonathan J. Hull , Dar-Shyang Lee , Gregory J. Wolff
IPC分类号： G06F3/12 , G06F15/00
CPC分类号： G06K9/00442 , G06K9/325 , G06K9/38 , G06K2209/01 , G06T5/00
摘要： A printing system enables the printing of enhanced documents using a semantic classification scheme. A printing system receives an image to be printed. The system classifies the image according to the semantic classification scheme and, based on this classification, performs enhancement processing on the image. Depending on the desired application, the printing system may recognize and classify any number of image types and may then perform various enhancement processing functions on the image, where the type of enhancement processing performed is based on the classification of the image.

7. 发明授权

US08281230B2 Techniques for storing multimedia information with source documents 有权
标题翻译：使用源文档存储多媒体信息的技术
公开(公告)号：US08281230B2
公开(公告)日：2012-10-02
申请号：US11843863
申请日：2007-08-23
申请人： Berna Erol , Jonathan Hull , Dar-Shyang Lee
发明人： Berna Erol , Jonathan Hull , Dar-Shyang Lee
IPC分类号： G06F17/00 , G06F17/30
CPC分类号： G06F17/30056 , Y10S707/99945 , Y10S707/99948
摘要： A method of storing information for recorded information and a source document is provided. The method comprises: determining a first piece of information included in the recorded information; determining at least a first source document from one or more source documents that comprises information that matches the first piece of information; and storing information identifying the recorded information, information representative of the first piece of information, and information identifying the first source document such that the information identifying the first source document can be determined given the information identifying the recorded information and the information representative of the first piece of information.
摘要翻译：提供了一种存储用于记录信息和源文档的信息的方法。该方法包括：确定包含在记录信息中的第一条信息; 从包括与所述第一信息匹配的信息的一个或多个源文档确定至少第一源文档; 以及存储识别记录信息的信息，表示第一条信息的信息，以及识别第一源文档的信息，使得能够根据识别记录信息的信息和表示第一源文档的信息来确定识别第一源文档的信息信息片段。

8. 发明授权

US07991778B2 Triggering actions with captured input in a mixed media environment 有权
标题翻译：在混合媒体环境中触发捕获的输入操作
公开(公告)号：US07991778B2
公开(公告)日：2011-08-02
申请号：US11461024
申请日：2006-07-31
申请人： Jonathan J. Hull , Berna Erol , Jamey Graham , Peter E. Hart , Dar-Shyang Lee , Kurt Piersol
发明人： Jonathan J. Hull , Berna Erol , Jamey Graham , Peter E. Hart , Dar-Shyang Lee , Kurt Piersol
IPC分类号： G06F17/30
CPC分类号： G06K9/00442 , H04N1/32133 , H04N2201/3226 , H04N2201/3249 , H04N2201/3269
摘要： A Mixed Media Reality (MMR) system and associated techniques provide mechanisms for forming a mixed media document that includes media of at least two types (e.g., printed paper as a first medium and digital content and/or web link as a second medium). The MMR system includes an action processor and methods, and an MMR document with having an associated action. The MMR document specifies different actions for different MMR documents, and creates any number of MMR documents for a particular location on any media, thereby allowing the MMR architecture to serve as a universal trigger or initiator for additional processing. The action processor receives the output of the MMR recognition process which yields an MMR document including at least one action. The action processor executes that action which includes various commands to the MMR system or other systems coupled to the MMR system. The MMR system architecture can perform action such as retrieving the electronic form of the document to the capture device, retrieving the specification for the action, inserting data to a MMR document, transferring data between documents, purchasing items, authoring actions or reviewing historical information about actions.
摘要翻译：混合媒体现实（MMR）系统和相关技术提供了用于形成包括至少两种类型（例如作为第一媒体的打印纸和作为第二媒体的数字内容和/或网络链接的打印纸）的混合媒体文档的机制。 MMR系统包括动作处理器和方法以及具有相关动作的MMR文档。 MMR文档为不同的MMR文档规定了不同的操作，并为任何媒体上的特定位置创建了任意数量的MMR文档，从而允许MMR架构作为通用触发器或启动器进行额外处理。动作处理器接收MMR识别过程的输出，其产生包括至少一个动作的MMR文档。动作处理器执行包括各种命令到MMR系统或耦合到MMR系统的其他系统的动作。 MMR系统架构可以执行诸如将文档的电子表单检索到捕获设备，检索操作的规范，将数据插入MMR文档，在文档之间传送数据，购买项目，创作动作或者查看关于行动。

9. 发明授权

US07899249B2 Media material analysis of continuing article portions 有权
标题翻译：继续文章部分的媒体材料分析
公开(公告)号：US07899249B2
公开(公告)日：2011-03-01
申请号：US11644009
申请日：2006-12-22
申请人： Ralph Furmaniak , Ray Smith , Luc Vincent , Dan Bloomberg , Dar-Shyang Lee
发明人： Ralph Furmaniak , Ray Smith , Luc Vincent , Dan Bloomberg , Dar-Shyang Lee
IPC分类号： G06K9/34
CPC分类号： G06K9/00469
摘要： The present invention relates to systems and methods for analyzing media material having articles continuing across multiple pages. A media material analyzer includes a segmenter and an article composer. The segmenter identifies block segments associated with columnar body test in the media material. The article composer determines which of the identified block segments belong to a continuing article extending across multiple pages in the media material based on language statistics information and continuation transition information.
摘要翻译：本发明涉及用于分析介质材料的系统和方法，所述介质材料具有跨越多页的物品。媒体材料分析器包括分割器和文章作曲者。分割器识别与介质材料中柱状体测试相关的块段。文章作曲者基于语言统计信息和连续转换信息确定哪些识别的块段属于在媒体材料中的多个页面上延伸的连续文章。

10. 发明授权

US07606444B1 Multimodal access of meeting recordings 有权
标题翻译：多式联运会议录音
公开(公告)号：US07606444B1
公开(公告)日：2009-10-20
申请号：US11942706
申请日：2007-11-19
申请人： Berna Erol , Jamey Graham , Jonathan J. Hull , Dar-Shyang Lee
发明人： Berna Erol , Jamey Graham , Jonathan J. Hull , Dar-Shyang Lee
IPC分类号： G06K9/54 , G06K9/60
CPC分类号： G06K9/00711 , G11B27/034 , G11B27/28 , G11B27/34 , Y10S707/99931
摘要： A meeting recorder captures multimodal information of a meeting. Subsequent analysis of the information produces scores indicative of visually and aurally significant events that can help identify significant segments of the meeting recording. Textual analysis can enhance searching for significant meeting segments and otherwise enhance the presentation of the meeting segments.
摘要翻译：会议记录器捕获会议的多模态信息。对信息的后续分析产生指示视觉和听觉显着事件的分数，其可以帮助识别会议记录的重要部分。文本分析可以加强对重要会议部分的搜索，从而增强会议部分的呈现。

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