公开(公告)号：US11816182B2

公开(公告)日：2023-11-14

申请号：US17340794

申请日：2021-06-07

Applicant: SAP SE

Inventor： Marco Spinaci ,  Marek Polewczyk

IPC: G06F18/214 ,  G06V30/28

CPC classification number: G06F18/214 ,  G06V30/287

Abstract: The present disclosure provides techniques for encoding and decoding characters for optical character recognition. The techniques involve determining sets of numbers for encoding a character set where each number in a particular set of numbers for encoding a particular character is mapped to a graphical unit (e.g., radical) of the particular character. A mapping between each set of numbers in the possible encodings and the character set may be determined based the closest character already encoded. A machine learning model may be trained to perform optical character recognition using training data labeled using the set of encodings and the mappings.

公开(公告)号：US20250131761A1

公开(公告)日：2025-04-24

申请号：US18381874

申请日：2023-10-19

Applicant: SAP SE

Inventor： Marek Polewczyk ,  Marco Spinaci

IPC: G06V30/416 ,  G06V30/10 ,  G06V30/412

Abstract: Various examples are directed to systems and methods for determining table data from a document image depicting a plurality of words and at least one table comprising at least a portion of the plurality of words. For example, Optical Character Recognition (OCR) data may be determined based on the document image. A table detection model may be executed based at least in part on the OCR data.

公开(公告)号：US20230222632A1

公开(公告)日：2023-07-13

申请号：US17570678

申请日：2022-01-07

Applicant: SAP SE

Inventor： Marek Polewczyk ,  Marco Spinaci

IPC: G06T5/00 ,  G06V30/414 ,  G06V10/774 ,  G06V30/16

CPC classification number: G06T5/006 ,  G06V10/774 ,  G06V30/414 ,  G06V30/1607 ,  G06T2207/10008 ,  G06T2207/20081 ,  G06T2207/30176

Abstract: A method may include determining, based at least on an image of a document, a plurality of text bounding boxes enclosing lines of text present in the document. A machine learning model may be trained to determine, based at least on the coordinates defining the text bounding boxes, the coordinates of a document bounding box enclosing the text bounding boxes. The document bounding box may encapsulate the visual aberrations that are present in the image of the document. As such, one or more transformations may be determined based on the coordinates of the document bounding box. The image of the document may be deskewed by applying the transformations. One or more downstream tasks may be performed based on the deskewed image of the document. Related methods and articles of manufacture are also disclosed.

公开(公告)号：US12165298B2

公开(公告)日：2024-12-10

申请号：US17570678

申请日：2022-01-07

Applicant: SAP SE

Inventor： Marek Polewczyk ,  Marco Spinaci

IPC: G06T5/80 ,  G06V10/774 ,  G06V30/16 ,  G06V30/414

Abstract: A method may include determining, based at least on an image of a document, a plurality of text bounding boxes enclosing lines of text present in the document. A machine learning model may be trained to determine, based at least on the coordinates defining the text bounding boxes, the coordinates of a document bounding box enclosing the text bounding boxes. The document bounding box may encapsulate the visual aberrations that are present in the image of the document. As such, one or more transformations may be determined based on the coordinates of the document bounding box. The image of the document may be deskewed by applying the transformations. One or more downstream tasks may be performed based on the deskewed image of the document. Related methods and articles of manufacture are also disclosed.

公开(公告)号：US20220391637A1

公开(公告)日：2022-12-08

申请号：US17340794

申请日：2021-06-07

Applicant: SAP SE

Inventor： Marco Spinaci ,  Marek Polewczyk

IPC: G06K9/62

Abstract: The present disclosure provides techniques for encoding and decoding characters for optical character recognition. The techniques involve determining sets of numbers for encoding a character set where each number in a particular set of numbers for encoding a particular character is mapped to a graphical unit (e.g., radical) of the particular character. A mapping between each set of numbers in the possible encodings and the character set may be determined based the closest character already encoded. A machine learning model may be trained to perform optical character recognition using training data labeled using the set of encodings and the mappings.