公开(公告)号：US09678989B2

公开(公告)日：2017-06-13

申请号：US14683763

申请日：2015-04-10

Applicant: Google Inc.

Inventor： Salih Burak Gokturk ,  Munjal Shah ,  Azhar Khan

IPC: G06K9/00 ,  G06F17/30 ,  G06Q30/02 ,  G06K9/62 ,  G06F3/0484

CPC classification number: G06F17/30256 ,  G06F3/04842 ,  G06F3/04847 ,  G06F17/3025 ,  G06F17/30259 ,  G06F17/30268 ,  G06F17/30277 ,  G06K9/00664 ,  G06K9/6201 ,  G06K9/6202 ,  G06Q30/0225

Abstract: An index is provided that holds information about each image content item in a collection of items, For each image content item, a first information item identifying the image content item and its location on a network, and at least one of (i) a second information item identifying a signature value of an object in the image content, or (ii) identification of a recognized object in the image content.

公开(公告)号：US09430719B2

公开(公告)日：2016-08-30

申请号：US14855826

申请日：2015-09-16

Applicant: Google Inc.

Inventor： Salih Burak Gokturk ,  Dragomir Anguelov ,  Vincent O. Vanhoucke ,  Kuang-chih Lee ,  Diem Thanh Vu ,  Danny Yang ,  Munjal Shah ,  Azhar Khan

IPC: G06K9/00 ,  G06K9/62 ,  G06F17/30 ,  G06F3/0482

CPC classification number: G06K9/6218 ,  G06F3/0482 ,  G06F17/30247 ,  G06F17/30253 ,  G06F17/30256 ,  G06F17/30265 ,  G06K9/00228 ,  G06K9/00288 ,  G06K9/00375 ,  G06K9/00671 ,  G06K9/6215 ,  G06K9/6267

Abstract: An embodiment provides for enabling retrieval of a collection of captured images that form at least a portion of a library of images. For each image in the collection, a captured image may be analyzed to recognize information from image data contained in the captured image, and an index may be generated, where the index data is based on the recognized information. Using the index, functionality such as search and retrieval is enabled. Various recognition techniques, including those that use the face, clothing, apparel, and combinations of characteristics may be utilized. Recognition may be performed on, among other things, persons and text carried on objects.

公开(公告)号：US20140369626A1

公开(公告)日：2014-12-18

申请号：US14153636

申请日：2014-01-13

Applicant: Google Inc.

Inventor： Salih Burak Gokturk ,  Dragomir Anguelov ,  Vincent Vanhoucke ,  Kuang-chih Lee ,  Diem Vu ,  Danny Yang ,  Munjal Shah ,  Azhar Khan

IPC: G06F17/30

CPC classification number: G06K9/6218 ,  G06F3/0482 ,  G06F17/30247 ,  G06F17/30253 ,  G06F17/30256 ,  G06F17/30265 ,  G06K9/00228 ,  G06K9/00288 ,  G06K9/00375 ,  G06K9/00671 ,  G06K9/6215 ,  G06K9/6267

Abstract: An embodiment provides for enabling retrieval of a collection of captured images that form at least a portion of a library of images. For each image in the collection, a captured image may be analyzed to recognize information from image data contained in the captured image, and an index may be generated, where the index data is based on the recognized information. Using the index, functionality such as search and retrieval is enabled. Various recognition techniques, including those that use the face, clothing, apparel, and combinations of characteristics may be utilized. Recognition may be performed on, among other things, persons and text carried on objects.

Abstract translation: 实施例提供了能够检索形成图像库的至少一部分的所捕获图像的集合。 对于集合中的每个图像，可以分析捕获的图像以从捕获图像中包含的图像数据识别信息，并且可以生成索引，其中索引数据基于所识别的信息。 使用索引，启用搜索和检索等功能。 可以使用各种识别技术，包括使用面部，服装，服装和特征组合的识别技术。 在其他情况下，可以执行承认对象上的人和文本。

公开(公告)号：US09171013B2

公开(公告)日：2015-10-27

申请号：US14153636

申请日：2014-01-13

Applicant: Google Inc.

Inventor： Salih Burak Gokturk ,  Dragomir Anguelov ,  Vincent Vanhoucke ,  Kuang-chih Lee ,  Diem Vu ,  Danny Yang ,  Munjal Shah ,  Azhar Khan

IPC: G06K9/60 ,  G06F17/30 ,  G06K9/00

CPC classification number: G06K9/6218 ,  G06F3/0482 ,  G06F17/30247 ,  G06F17/30253 ,  G06F17/30256 ,  G06F17/30265 ,  G06K9/00228 ,  G06K9/00288 ,  G06K9/00375 ,  G06K9/00671 ,  G06K9/6215 ,  G06K9/6267

Abstract: An embodiment provides for enabling retrieval of a collection of captured images that form at least a portion of a library of images. For each image in the collection, a captured image may be analyzed to recognize information from image data contained in the captured image, and an index may be generated, where the index data is based on the recognized information. Using the index, functionality such as search and retrieval is enabled. Various recognition techniques, including those that use the face, clothing, apparel, and combinations of characteristics may be utilized. Recognition may be performed on, among other things, persons and text carried on objects.

Abstract translation: 实施例提供了能够检索形成图像库的至少一部分的所捕获图像的集合。 对于集合中的每个图像，可以分析捕获的图像以从捕获的图像中包含的图像数据识别信息，并且可以生成索引，其中索引数据基于所识别的信息。 使用索引，启用搜索和检索等功能。 可以使用各种识别技术，包括使用面部，服装，服装和特征组合的识别技术。 在其他情况下，可以执行承认对象上的人和文本。

公开(公告)号：US20150213062A1

公开(公告)日：2015-07-30

申请号：US14683763

申请日：2015-04-10

Applicant: Google Inc.

Inventor： Salih Burak Gokturk ,  Munjal Shah ,  Azhar Khan

IPC: G06F17/30 ,  G06K9/62 ,  G06F3/0484

CPC classification number: G06F17/30256 ,  G06F3/04842 ,  G06F3/04847 ,  G06F17/3025 ,  G06F17/30259 ,  G06F17/30268 ,  G06F17/30277 ,  G06K9/00664 ,  G06K9/6201 ,  G06K9/6202 ,  G06Q30/0225

Abstract: An index is provided that holds information about each image content item in a collection of items, For each image content item, a first information item identifying the image content item and its location on a network, and at least one of (i) a second information item identifying a signature value of an object in the image content, or (ii) identification of a recognized object in the image content.

Abstract translation: 提供索引，其保存关于项目集合中的每个图像内容项目的信息。对于每个图像内容项目，标识图像内容项目的第一信息项目及其在网络上的位置，以及（i）第二 识别图像内容中的对象的签名值的信息项，或（ii）图像内容中的识别对象的识别。

公开(公告)号：US20160125270A1

公开(公告)日：2016-05-05

申请号：US14855826

申请日：2015-09-16

Applicant: Google Inc.

Inventor： Salih Burak Gokturk ,  Dragomir Anguelov ,  Vincent O. Vanhoucke ,  Kuang-chih Lee ,  Diem Thanh Vu ,  Danny Yang ,  Munjal Shah ,  Azhar Khan

IPC: G06K9/62 ,  G06F3/0482 ,  G06F17/30 ,  G06K9/00

CPC classification number: G06K9/6218 ,  G06F3/0482 ,  G06F17/30247 ,  G06F17/30253 ,  G06F17/30256 ,  G06F17/30265 ,  G06K9/00228 ,  G06K9/00288 ,  G06K9/00375 ,  G06K9/00671 ,  G06K9/6215 ,  G06K9/6267

Abstract: An embodiment provides for enabling retrieval of a collection of captured images that form at least a portion of a library of images. For each image in the collection, a captured image may be analyzed to recognize information from image data contained in the captured image, and an index may be generated, where the index data is based on the recognized information. Using the index, functionality such as search and retrieval is enabled. Various recognition techniques, including those that use the face, clothing, apparel, and combinations of characteristics may be utilized. Recognition may be performed on, among other things, persons and text carried on objects.

Abstract translation: 实施例提供了能够检索形成图像库的至少一部分的所捕获图像的集合。 对于集合中的每个图像，可以分析捕获的图像以从捕获图像中包含的图像数据识别信息，并且可以生成索引，其中索引数据基于所识别的信息。 使用索引，启用搜索和检索等功能。 可以使用各种识别技术，包括使用面部，服装，服装和特征组合的识别技术。 在其他情况下，可以执行承认对象上的人和文本。