公开(公告)号：US09898845B2

公开(公告)日：2018-02-20

申请号：US14791070

申请日：2015-07-02

申请人： CANON KABUSHIKI KAISHA

发明人： Hiromasa Kawasaki ,  Tadanori Nakatsuka ,  Kinya Honda ,  Taeko Yamazaki

IPC分类号： G06K9/00 ,  G06T11/60 ,  G06T11/20 ,  G06K9/32

CPC分类号： G06T11/60 ,  G06K9/00456 ,  G06K9/00463 ,  G06K9/3275 ,  G06K2009/00489 ,  G06K2209/01 ,  G06T11/203 ,  G06T11/206 ,  G06T2210/22

摘要： In a case where a position of a recognized cell is shifted from a position of a ruled line of an actual cell, if the recognized cell is deleted, a part of the ruled line of the actual cell is deleted. According to an aspect of the present invention, straight lines are detected from regions around four sides constituting the recognized cell, and an inside of a region surrounded by the detected straight lines is deleted.

公开(公告)号：US09881223B2

公开(公告)日：2018-01-30

申请号：US14258276

申请日：2014-04-22

申请人： Lenovo (Singapore) Pte. Ltd.

发明人： Robert James Kapinos ,  Xin Feng ,  Paul Hilburger

IPC分类号： G06K9/32 ,  G06K9/00

CPC分类号： G06K9/3258 ,  G06K9/00671 ,  G06K2009/00489

摘要： An embodiment provides a method, including: capturing, using an image capture device of an electronic device, image data of a document; processing, using a processor, the image data; the processing including identifying text within the image data to form two or more images into a composite document of the document; and storing, in a memory, data related to the composite document. Other aspects are described and claimed.

公开(公告)号：US20180018773A1

公开(公告)日：2018-01-18

申请号：US15650049

申请日：2017-07-14

申请人： Siemens Healthcare GmbH

发明人： Valer Canda

IPC分类号： G06T7/00 ,  G06K9/00

CPC分类号： G06T7/10 ,  G06K2009/00489 ,  G06T7/136 ,  G06T7/174 ,  G06T7/97 ,  G06T2207/10088 ,  G16H30/20 ,  G16H40/63

摘要： For the determination of an image series from a set of a number of image series, in each case of a signature is compiled for each of the number of image series. This signature is formed from a set of attributes of the respective image series. A signature from the signatures for the image series is ascertained that is most similar to a prespecified signature set. An action is performed with the image series whose signature was ascertained as the most similar signature.

公开(公告)号：US09378413B2

公开(公告)日：2016-06-28

申请号：US14304162

申请日：2014-06-13

申请人： FUJI XEROX CO., LTD.

发明人： Kohshiro Inomata

IPC分类号： G06K1/00 ,  G06K9/00

CPC分类号： H04N1/387 ,  G06F17/30047 ,  G06F17/30247 ,  G06K9/00442 ,  G06K9/00456 ,  G06K9/00483 ,  G06K9/00496 ,  G06K9/00536 ,  G06K9/6201 ,  G06K9/6215 ,  G06K15/1889 ,  G06K2009/00489 ,  G06K2009/6213 ,  G06T11/60 ,  H04N1/32128 ,  H04N1/40012 ,  H04N1/56

摘要： An image processing apparatus is provided. The image processing apparatus includes a data receiver, an image specifier, a replacement specifier, and a data generator. The data receiver receives data. The image specifier specifies a first image contained in the data. The replacement specifier specifies replacement data for the first image on the basis of a characteristic of the data. The data generator generates data in which the first image has been replaced with an image represented by the replacement data.

摘要翻译： 提供一种图像处理装置。 图像处理装置包括数据接收器，图像说明符，替换说明符和数据发生器。 数据接收器接收数据。 图像说明符指定数据中包含的第一个图像。 替换说明符基于数据的特性来指定第一图像的替换数据。 数据生成器生成其中用替换数据表示的图像替换第一图像的数据。

公开(公告)号：US20160034753A1

公开(公告)日：2016-02-04

申请号：US14803338

申请日：2015-07-20

申请人： KYOCERA Document Solutions Inc.

发明人： Hiroyuki Harada

IPC分类号： G06K9/00 ,  G06T7/00 ,  G06K9/68

CPC分类号： G06T7/10 ,  G06K9/344 ,  G06K9/6828 ,  G06K2009/00489 ,  G06T5/005

摘要： In an image processing apparatus, a character recognizing unit identifies a character image in a document image. A font matching unit determines a character code and a font type corresponding to the identified character image. A fore-and-background setting unit sets the document image as a background image and sets a standard character image based on the determined character code and the determined font type. A background image correcting unit (a) deletes a deletion area in the background image, the deletion area taking a same position as the character image or the standard character image, (b) interpolates a differential area between the character image and the standard character image in a specific neighborhood area that contacts with the deletion area on the basis of the background image, and (c) interpolates the deletion area on the basis of the back ground image.

摘要翻译： 在图像处理装置中，字符识别单元识别文档图像中的字符图像。 字体匹配单元确定与所识别的字符图像相对应的字符代码和字体类型。 前后设置单元将文档图像设置为背景图像，并且基于确定的字符代码和确定的字体类型来设置标准字符图像。 背景图像校正单元（a）删除背景图像中的删除区域，与字符图像或标准字符图像相同位置的删除区域，（b）内插字符图像与标准字符图像之间的差分区域 在与所述背景图像的基础上与所述删除区域接触的特定邻域中，以及（c）基于所述背景图像来内插所述删除区域。

公开(公告)号：US20140267642A1

公开(公告)日：2014-09-18

申请号：US14135727

申请日：2013-12-20

申请人： Yonatan Wexler ,  Amnon Shashua

发明人： Yonatan Wexler ,  Amnon Shashua

IPC分类号： G09B21/00 ,  G06K9/00

CPC分类号： G06K9/3275 ,  A61F9/08 ,  G01B11/24 ,  G02C11/10 ,  G06F3/011 ,  G06F3/16 ,  G06F17/2765 ,  G06K9/00221 ,  G06K9/00288 ,  G06K9/00442 ,  G06K9/00463 ,  G06K9/00469 ,  G06K9/00483 ,  G06K9/00671 ,  G06K9/00852 ,  G06K9/2081 ,  G06K9/22 ,  G06K9/30 ,  G06K9/3233 ,  G06K9/3241 ,  G06K9/325 ,  G06K9/3283 ,  G06K9/74 ,  G06K2009/00489 ,  G06K2009/2045 ,  G08B3/10 ,  G08B6/00 ,  G09B21/00 ,  G09B21/001 ,  G09B21/003 ,  G09B21/006 ,  G10L13/043 ,  H04N5/2251 ,  H04N5/2252 ,  H04N5/23229 ,  H04N5/23232

摘要： A device and method are provided for audible facial recognition. In one implementation, an apparatus for aiding a visually impaired user to identify individuals is provided. The apparatus may include a portable image sensor configured to be worn by the visually impaired user and to capture real-time image data from an environment of the user. The apparatus may also include at least one portable processor device configured to determine an existence of face-identifying information in the real-time image data, and access stored facial information and audible indicators. The at least one portable processor device may also be configured to compare the face-identifying information with the stored facial information, and identify a match. Based on the match, the at least one portable processor may be configured to cause an audible indicator to be announced to the visually impaired user.

摘要翻译： 提供用于可听见的面部识别的装置和方法。 在一个实现中，提供了一种用于帮助视觉障碍用户识别个人的装置。 该装置可以包括便携式图像传感器，该便携式图像传感器被配置为由视觉受损的用户佩戴并且从用户的环境捕获实时图像数据。 该装置还可以包括至少一个便携式处理器装置，其被配置为确定实时图像数据中的面部识别信息的存在，以及访问存储的面部信息和可听见的指示符。 所述至少一个便携式处理器装置还可以被配置为将所述面部识别信息与所存储的面部信息进行比较，并且识别匹配。 基于该匹配，所述至少一个便携式处理器可以被配置为使得可视指示符被通知给视障者。

公开(公告)号：US20180344242A1

公开(公告)日：2018-12-06

申请号：US16059498

申请日：2018-08-09

申请人： Happify, Inc.

发明人： TOMER BEN-KIKI ,  Ran Zilca

IPC分类号： A61B5/00 ,  G06K9/00 ,  G06F17/27 ,  G10L15/22 ,  A61M21/02 ,  A61B5/16

CPC分类号： A61B5/4833 ,  A61B5/165 ,  A61B5/4836 ,  A61B5/7425 ,  A61M21/02 ,  A61M2021/0027 ,  A61M2021/005 ,  A61M2205/3303 ,  A61M2205/3375 ,  A61M2205/3553 ,  A61M2205/3584 ,  A61M2205/502 ,  A61M2205/505 ,  A61M2205/52 ,  A61M2230/50 ,  A61M2230/63 ,  G06F17/2785 ,  G06K9/00442 ,  G06K2009/00489 ,  G10L15/22

摘要： A computing system/method for enabling a user to improve, via training, a system designed to increase the emotional and/or physical well-being of persons, or designed for other purposes. The system/method includes retrieving a user response from a dialogue database, the user response having already labeled thereto an assigned class having a highest confidence score, the confidence score indicating degree of confidence that context of the retrieved user response is of the assigned class, displaying, the assigned class, along with other classes each having a respective lower confidence score, and receiving an indication of validity of the assigned class. The system/method further includes retrieving of a pair of sequential user response and follow-up prompt from the database, displaying user-selectable ratings, each rating designating a respectively different quality to the follow-up prompt, receiving selection of a rating and a related comment, and associating the selection and the comment to the follow-up prompt.

公开(公告)号：US09723174B2

公开(公告)日：2017-08-01

申请号：US15142751

申请日：2016-04-29

申请人： FUJI XEROX CO., LTD.

发明人： Kohshiro Inomata

IPC分类号： H04N1/387 ,  H04N1/40 ,  H04N1/56 ,  G06K15/02 ,  G06K9/00 ,  G06K9/62 ,  G06F17/30 ,  G06T11/60 ,  H04N1/32

CPC分类号： H04N1/387 ,  G06F17/30047 ,  G06F17/30247 ,  G06K9/00442 ,  G06K9/00456 ,  G06K9/00483 ,  G06K9/00496 ,  G06K9/00536 ,  G06K9/6201 ,  G06K9/6215 ,  G06K15/1889 ,  G06K2009/00489 ,  G06K2009/6213 ,  G06T11/60 ,  H04N1/32128 ,  H04N1/40012 ,  H04N1/56

摘要： An image processing apparatus is provided. The image processing apparatus includes a data receiver, an image specifier, a replacement specifier, and a data generator. The data receiver receives data. The image specifier specifies a first image contained in the data. The replacement specifier specifies replacement data for the first image on the basis of a characteristic of the data. The data generator generates data in which the first image has been replaced with an image represented by the replacement data.

公开(公告)号：US09542613B2

公开(公告)日：2017-01-10

申请号：US14135928

申请日：2013-12-20

申请人： Yonatan Wexler ,  Amnon Shashua

发明人： Yonatan Wexler ,  Amnon Shashua

IPC分类号： H04N5/232 ,  G06K9/32 ,  G09B21/00 ,  G06K9/00 ,  G06K9/22 ,  A61F9/08 ,  G08B3/10 ,  G08B6/00 ,  G06F17/27 ,  G06K9/74 ,  G10L13/04 ,  G06F3/16 ,  G06F3/01 ,  H04N5/225 ,  G06K9/20 ,  G01B11/24 ,  G06T7/00 ,  G06K9/30 ,  G02C11/00

CPC分类号： G06K9/3275 ,  A61F9/08 ,  G01B11/24 ,  G02C11/10 ,  G06F3/011 ,  G06F3/16 ,  G06F17/2765 ,  G06K9/00221 ,  G06K9/00288 ,  G06K9/00442 ,  G06K9/00463 ,  G06K9/00469 ,  G06K9/00483 ,  G06K9/00671 ,  G06K9/00852 ,  G06K9/2081 ,  G06K9/22 ,  G06K9/30 ,  G06K9/3233 ,  G06K9/3241 ,  G06K9/325 ,  G06K9/3283 ,  G06K9/74 ,  G06K2009/00489 ,  G06K2009/2045 ,  G08B3/10 ,  G08B6/00 ,  G09B21/00 ,  G09B21/001 ,  G09B21/003 ,  G09B21/006 ,  G10L13/043 ,  H04N5/2251 ,  H04N5/2252 ,  H04N5/23229 ,  H04N5/23232

摘要： A apparatus and method are provided for processing images. In one embodiment, the apparatus includes an image sensor configured to capture real time images from an environment of a user. The apparatus also includes a mobile power source, and at least one processor device configured to process, at an initial resolution, images to determine existence of a trigger, and access rules associating image context with image capture resolution to enable images of a first context to be processed at a lower capture resolution than images of a second context. The processor device analyzes at least one first image, selects a first image capture resolution rule, and applies the first image capture resolution rule to a subsequent captured image. The processor device analyzes at least one second image, selects a second image capture resolution rule, and applies the second image capture resolution rule to a second subsequent captured image.

摘要翻译： 提供了一种用于处理图像的装置和方法。 在一个实施例中，该装置包括被配置为从用户的环境捕获实时图像的图像传感器。 该装置还包括移动电源，以及至少一个处理器装置，被配置为以初始分辨率处理图像以确定触发的存在，以及将图像上下文与图像捕获分辨率相关联的访问规则，以使得第一上下文的图像能够 以比第二上下文的图像更低的捕获分辨率进行处理。 处理器设备分析至少一个第一图像，选择第一图像捕获分辨率规则，并将第一图像捕获分辨率规则应用于后续捕获的图像。 处理器设备分析至少一个第二图像，选择第二图像捕获分辨率规则，并将第二图像捕获分辨率规则应用于第二后续捕获图像。

公开(公告)号：US09436887B2

公开(公告)日：2016-09-06

申请号：US14137373

申请日：2013-12-20

申请人： Yonatan Wexler ,  Erez Na'Aman ,  Amnon Shashua

发明人： Yonatan Wexler ,  Erez Na'Aman ,  Amnon Shashua

IPC分类号： H04N9/47 ,  H04N7/18 ,  G06K9/32 ,  G09B21/00 ,  G06K9/00 ,  G06K9/22 ,  A61F9/08 ,  H04N5/232 ,  G08B3/10 ,  G08B6/00 ,  G06F17/27 ,  G06K9/74 ,  G10L13/04 ,  G06F3/16 ,  G06F3/01 ,  H04N5/225 ,  G06K9/20 ,  G01B11/24 ,  G06T7/00 ,  G06K9/30 ,  G02C11/00

CPC分类号： G06K9/3275 ,  A61F9/08 ,  G01B11/24 ,  G02C11/10 ,  G06F3/011 ,  G06F3/16 ,  G06F17/2765 ,  G06K9/00221 ,  G06K9/00288 ,  G06K9/00442 ,  G06K9/00463 ,  G06K9/00469 ,  G06K9/00483 ,  G06K9/00671 ,  G06K9/00852 ,  G06K9/2081 ,  G06K9/22 ,  G06K9/30 ,  G06K9/3233 ,  G06K9/3241 ,  G06K9/325 ,  G06K9/3283 ,  G06K9/74 ,  G06K2009/00489 ,  G06K2009/2045 ,  G08B3/10 ,  G08B6/00 ,  G09B21/00 ,  G09B21/001 ,  G09B21/003 ,  G09B21/006 ,  G10L13/043 ,  H04N5/2251 ,  H04N5/2252 ,  H04N5/23229 ,  H04N5/23232

摘要： Devices and a method are provided for providing context-related feedback to a user. In one implementation, the method comprises capturing real time image data from an environment of the user. The method further comprises identifying in the image data a hand-related trigger. Multiple context-based alternative actions are associated with the hand-related trigger. Further, the method comprises identifying in the image data an object associated with the hand-related trigger. The object is further associated with a particular context. Also, the method comprises selecting one of the multiple alternative actions based on the particular context. The method further comprises outputting the context-related feedback based on a result of the executed alternative action.

摘要翻译： 提供了用于向用户提供与情境有关的反馈的设备和方法。 在一个实现中，该方法包括从用户的环境捕获实时图像数据。 该方法还包括在图像数据中识别与手相关的触发。 多个基于上下文的替代动作与手动触发相关联。 此外，该方法包括在图像数据中识别与手动触发相关联的对象。 该对象进一步与特定上下文相关联。 此外，该方法包括基于特定上下文选择多个替代动作中的一个。 该方法还包括基于所执行的备选动作的结果来输出与上下文有关的反馈。