公开(公告)号：US11847563B2

公开(公告)日：2023-12-19

申请号：US17970651

申请日：2022-10-21

Applicant: OPEN TEXT SA ULC

Inventor： Christopher Dale Lund

IPC: H04N1/387 ,  G06N3/08 ,  H04N1/40 ,  G06N20/00 ,  G06V30/148 ,  G06V30/414 ,  G06V30/19 ,  G06V10/82 ,  G06V10/24

CPC classification number: G06N3/08 ,  G06N20/00 ,  G06V10/242 ,  G06V10/82 ,  G06V30/153 ,  G06V30/19173 ,  G06V30/414 ,  H04N1/3877 ,  H04N1/40012

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

公开(公告)号：US20210306517A1

公开(公告)日：2021-09-30

申请号：US17347527

申请日：2021-06-14

Applicant: OPEN TEXT SA ULC

Inventor： Christopher Dale Lund

IPC: H04N1/387 ,  H04N1/40 ,  G06N20/00 ,  G06K9/00 ,  G06K9/34

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

公开(公告)号：US20240070462A1

公开(公告)日：2024-02-29

申请号：US18503832

申请日：2023-11-07

Applicant: Open Text SA ULC

Inventor： Christopher Dale Lund

IPC: G06N3/08 ,  G06N20/00 ,  G06V10/24 ,  G06V10/82 ,  G06V30/148 ,  G06V30/19 ,  G06V30/414 ,  H04N1/387 ,  H04N1/40

CPC classification number: G06N3/08 ,  G06N20/00 ,  G06V10/242 ,  G06V10/82 ,  G06V30/153 ,  G06V30/19173 ,  G06V30/414 ,  H04N1/3877 ,  H04N1/40012

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

公开(公告)号：US20230049296A1

公开(公告)日：2023-02-16

申请号：US17970651

申请日：2022-10-21

Applicant: OPEN TEXT SA ULC

Inventor： Christopher Dale Lund

IPC: H04N1/387 ,  H04N1/40 ,  G06N20/00 ,  G06V30/148 ,  G06V30/414

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

公开(公告)号：US11509795B2

公开(公告)日：2022-11-22

申请号：US17347527

申请日：2021-06-14

Applicant: OPEN TEXT SA ULC

Inventor： Christopher Dale Lund

IPC: H04N1/387 ,  H04N1/40 ,  G06N20/00 ,  G06V30/148 ,  G06V30/414

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

公开(公告)号：US11044382B2

公开(公告)日：2021-06-22

申请号：US16819741

申请日：2020-03-16

Applicant: OPEN TEXT SA ULC

Inventor： Christopher Dale Lund

IPC: H04N1/387 ,  H04N1/40 ,  G06N20/00 ,  G06K9/00 ,  G06K9/34

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.