公开(公告)号：US20210133436A1

公开(公告)日：2021-05-06

申请号：US17147324

申请日：2021-01-12

Applicant: Open Text Corporation

Inventor： Arnaud Gilles Flament ,  Christopher Dale Lund ,  Guillaume Bernard Serge Koch ,  Denis Eric Goupil

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/46 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Systems, methods, and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.

公开(公告)号：US11893777B2

公开(公告)日：2024-02-06

申请号：US17147324

申请日：2021-01-12

Applicant: Open Text Corporation

Inventor： Arnaud Gilles Flament ,  Christopher Dale Lund ,  Guillaume Bernard Serge Koch ,  Denis Eric Goupil

IPC: G06V10/82 ,  G06N3/08 ,  G06V30/413 ,  G06V30/414 ,  G06F18/213 ,  G06F18/214 ,  G06F18/2413 ,  G06N3/045 ,  G06V30/14 ,  G06V30/18 ,  G06V30/19 ,  G06V30/10

CPC classification number: G06V10/82 ,  G06F18/213 ,  G06F18/214 ,  G06F18/24143 ,  G06N3/045 ,  G06N3/08 ,  G06V30/1444 ,  G06V30/18057 ,  G06V30/19173 ,  G06V30/413 ,  G06V30/414 ,  G06V30/10

Abstract: Systems, methods, and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.

公开(公告)号：US10902252B2

公开(公告)日：2021-01-26

申请号：US16035307

申请日：2018-07-13

Applicant: Open Text Corporation

Inventor： Arnaud Gilles Flament ,  Christopher Dale Lund ,  Guillaume Bernard Serge Koch ,  Denis Eric Goupil

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/62 ,  G06N3/08 ,  G06K9/46 ,  G06N3/04 ,  G06K9/54

Abstract: Systems, methods and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.

公开(公告)号：US20190019020A1

公开(公告)日：2019-01-17

申请号：US16035307

申请日：2018-07-13

Applicant: Open Text Corporation

Inventor： Arnaud Gilles Flament ,  Christopher Dale Lund ,  Guillaume Bernard Serge Koch ,  Denis Eric Goupil

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/62 ,  G06N3/08

Abstract: Systems, methods and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.

公开(公告)号：US12260632B2

公开(公告)日：2025-03-25

申请号：US18545885

申请日：2023-12-19

Applicant: Open Text Corporation

Inventor： Arnaud Gilles Flament ,  Christopher Dale Lund ,  Guillaume Bernard Serge Koch ,  Denis Eric Goupil

IPC: G06V10/82 ,  G06F18/214 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/08 ,  G06V30/14 ,  G06V30/18 ,  G06V30/19 ,  G06V30/413 ,  G06V30/414 ,  G06V30/10

Abstract: Systems, methods, and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.

公开(公告)号：US20240135700A1

公开(公告)日：2024-04-25

申请号：US18545885

申请日：2023-12-19

Applicant: Open Text Corporation

Inventor： Arnaud Gilles Flament ,  Christopher Dale Lund ,  Guillaume Bernard Serge Koch ,  Denis Eric Goupil

IPC: G06V10/82 ,  G06F18/213 ,  G06F18/214 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/08 ,  G06V30/14 ,  G06V30/18 ,  G06V30/19 ,  G06V30/413 ,  G06V30/414

CPC classification number: G06V10/82 ,  G06F18/213 ,  G06F18/214 ,  G06F18/24143 ,  G06N3/045 ,  G06N3/08 ,  G06V30/1444 ,  G06V30/18057 ,  G06V30/19173 ,  G06V30/413 ,  G06V30/414 ,  G06V30/10

Abstract: Systems, methods, and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.