-
Patent Agency Ranking
公开(公告)号：US20210117666A1
公开(公告)日：2021-04-22
申请号：US16655363
申请日：2019-10-17
Applicant: Adobe Inc.
Inventor： Verena Sabine Kaynig-Fittkau , Smitha Bangalore Naresh , Shawn Alan Gaither , Richard Cohn , Paul John Asente , Eylon Stroh , Emily Seminerio
Abstract: Techniques are provided for identifying structural elements of a document. One Methodology includes generating a first channel of rasterized content by rasterizing a full page of the document and generating one or more additional channels of rasterized content from the page of the document by rasterizing one or more corresponding content types from the page of the document. Each of the one or more additional channels includes a specific type of content that is different from each of the other one or more additional channels. The methodology further includes inputting the first channel of rasterized content and the one or more additional channels of rasterized content into a machine learning (ML) model. The methodology continues with determining location and classification for each of a plurality of structural elements on the page of the document using the ML model.
-
公开(公告)号：US11238312B2
公开(公告)日：2022-02-01
申请号：US16690695
申请日：2019-11-21
Applicant: Adobe Inc.
Inventor： Verena Kaynig-Fittkau , Sruthi Madapoosi Ravi , Richard Cohn , Nikolaos Barmpalios , Michael Kraley , Kanchana Sethu
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating diverse and realistic synthetic documents using deep learning. In particular, the disclosed systems can utilize a trained neural network to generate realistic image layouts comprising page elements that comply with layout parameters. The disclosed systems can also generate synthetic content corresponding to the page elements within the image layouts. The disclosed systems insert the synthetic content into the corresponding page elements of documents based on the image layouts to generate synthetic documents.
-
公开(公告)号：US11386685B2
公开(公告)日：2022-07-12
申请号：US16655363
申请日：2019-10-17
Applicant: Adobe Inc.
Inventor： Verena Sabine Kaynig-Fittkau , Smitha Bangalore Naresh , Shawn Alan Gaither , Richard Cohn , Paul John Asente , Eylon Stroh , Emily Seminerio
IPC: G06V30/413 , G06N20/00 , G06V30/412 , G06V30/414
Abstract: Techniques are provided for identifying structural elements of a document. One Methodology includes generating a first channel of rasterized content by rasterizing a full page of the document and generating one or more additional channels of rasterized content from the page of the document by rasterizing one or more corresponding content types from the page of the document. Each of the one or more additional channels includes a specific type of content that is different from each of the other one or more additional channels. The methodology further includes inputting the first channel of rasterized content and the one or more additional channels of rasterized content into a machine learning (ML) model. The methodology continues with determining location and classification for each of a plurality of structural elements on the page of the document using the ML model.
-
公开(公告)号：US10289655B2
公开(公告)日：2019-05-14
申请号：US15342852
申请日：2016-11-03
Applicant: ADOBE INC.
Inventor： James D. Pravetz , Richard Cohn , William Ie
Abstract: Active content is deterministically rendered in a stable format that is independent of any particular targeted environment, which the active content may subsequently be rendered to. Environmental and dynamic dependencies are removed from a specification associated with the active content for purposes of producing a stable and consistent specification for the active content. The stable and static specification is used to subsequently render the active content into the stable format for any targeted or desired environment.
-
公开(公告)号：US20210158093A1
公开(公告)日：2021-05-27
申请号：US16690695
申请日：2019-11-21
Applicant: Adobe Inc.
Inventor： Verena Kaynig-Fittkau , Sruthi Madapoosi Ravi , Richard Cohn , Nikolaos Barmpalios , Michael Kraley , Kanchana Sethu
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating diverse and realistic synthetic documents using deep learning. In particular, the disclosed systems can utilize a trained neural network to generate realistic image layouts comprising page elements that comply with layout parameters. The disclosed systems can also generate synthetic content corresponding to the page elements within the image layouts. The disclosed systems insert the synthetic content into the corresponding page elements of documents based on the image layouts to generate synthetic documents.
-
-
-
-
Search Results
5
records
(took 0.024 seconds)
