-
公开(公告)号：US20160012287A1
公开(公告)日：2016-01-14
申请号：US14861586
申请日：2015-09-22
Applicant: DROPBOX, INC.
Inventor： Tej Chajed , Peter Welinder , Boris Babekno , Dimitar Simeonov
CPC classification number: G06K9/00456 , G06K9/3275 , G06K9/4633 , G06K9/48 , G06T2207/20061
Abstract: Embodiments are provided for content item classification. In some embodiments, an image for classification is received, a compact representation for the image having values indicative of pixel values within the received image is generated, a plurality of angle measurements for possible edges of at least one potential document within the received image are determined, and the image is classified using said compact representation and said plurality of angle measurements
-
Patent Agency Ranking
公开(公告)号：US09558401B2
公开(公告)日：2017-01-31
申请号：US14861586
申请日：2015-09-22
Applicant: DROPBOX, INC.
Inventor： Tej Chajed , Peter Welinder , Boris Babenko , Dimitar Simeonov
CPC classification number: G06K9/00456 , G06K9/3275 , G06K9/4633 , G06K9/48 , G06T2207/20061
Abstract: Embodiments are provided for content item classification. In some embodiments, an image for classification is received, a compact representation for the image having values indicative of pixel values within the received image is generated, a plurality of angle measurements for possible edges of at least one potential document within the received image are determined, and the image is classified using said compact representation and said plurality of angle measurements.
Abstract translation: 为内容项分类提供实施例。 在一些实施例中，接收用于分类的图像，产生具有指示接收图像内的像素值的值的图像的紧凑表示，确定接收图像内的至少一个潜在文档的可能边缘的多个角度测量值 并且使用所述紧凑表示和所述多个角度测量对图像进行分类。
-
公开(公告)号：US20150071549A1
公开(公告)日：2015-03-12
申请号：US14022933
申请日：2013-09-10
Applicant: DROPBOX, INC.
Inventor： Tej Chajed , Peter Welinder , Boris Babekno , Dimitar Simeonov
CPC classification number: G06K9/00456 , G06K9/3275 , G06K9/4633 , G06K9/48 , G06T2207/20061
Abstract: Embodiments are provided for content item classification. In some embodiments, an image for classification is received, a compact representation for the image having values indicative of pixel values within the received image is generated, a plurality of angle measurements for possible edges of at least one potential document within the received image are determined, and the image is classified using said compact representation and said plurality of angle measurements
Abstract translation: 为内容项分类提供实施例。 在一些实施例中，接收用于分类的图像，产生具有指示接收图像内的像素值的值的图像的紧凑表示，确定接收图像内的至少一个潜在文档的可能边缘的多个角度测量值 并且使用所述紧凑表示和所述多个角度测量对图像进行分类
-
公开(公告)号：US09870422B2
公开(公告)日：2018-01-16
申请号：US13869930
申请日：2013-04-24
Applicant: Dropbox, Inc.
Inventor： Dimitar Simeonov , Joshua Blum , Max Kanter
CPC classification number: G06F17/30684 , G06F7/24
Abstract: Embodiments are provided for natural language search. In some embodiments, a content search request for content items related to an account with a content management system may be received, at least one filter from the content search query request may be determined to identify content items based on at least one of a management function and a content interaction function performed with a content item for the account, and the at least one filter may be applied to accessible content items for the account to identify content items.
-
公开(公告)号：US09171203B2
公开(公告)日：2015-10-27
申请号：US14022933
申请日：2013-09-10
Applicant: Dropbox, Inc.
Inventor： Tej Chajed , Peter Welinder , Boris Babekno , Dimitar Simeonov
CPC classification number: G06K9/00456 , G06K9/3275 , G06K9/4633 , G06K9/48 , G06T2207/20061
Abstract: Embodiments are provided for content item classification. In some embodiments, an image for classification is received, a compact representation for the image having values indicative of pixel values within the received image is generated, a plurality of angle measurements for possible edges of at least one potential document within the received image are determined, and the image is classified using said compact representation and said plurality of angle measurements.
Abstract translation: 为内容项分类提供实施例。 在一些实施例中，接收用于分类的图像，产生具有指示接收图像内的像素值的值的图像的紧凑表示，确定接收图像内的至少一个潜在文档的可能边缘的多个角度测量值 并且使用所述紧凑表示和所述多个角度测量对图像进行分类。
-
公开(公告)号：US20140317128A1
公开(公告)日：2014-10-23
申请号：US13869930
申请日：2013-04-24
Applicant: Dropbox, Inc.
Inventor： Dimitar Simeonov , Joshua Blum , Max Kanter
CPC classification number: G06F17/30684 , G06F7/24
Abstract: Embodiments are provided for natural language search. In some embodiments, a content search request for content items related to an account with a content management system may be received, at least one filter from the content search query request may be determined to identify content items based on at least one of a management function and a content interaction function performed with a content item for the account, and the at least one filter may be applied to accessible content items for the account to identify content items.
Abstract translation: 为自然语言搜索提供实施例。 在一些实施例中，可以接收与具有内容管理系统的帐户相关的内容项的内容搜索请求，来自内容搜索查询请求的至少一个过滤器可以被确定为基于管理功能中的至少一个来识别内容项 以及与该帐户的内容项目执行的内容交互功能，并且该至少一个过滤器可以应用于该帐户的可访问内容项以识别内容项目。
-
-
-
-
-
Search Results
6
records
(took 0.013 seconds)
