公开(公告)号：US11727697B2

公开(公告)日：2023-08-15

申请号：US17364343

申请日：2021-06-30

Applicant: salesforce.com, inc.

Inventor： Dennis Schultz ,  Daniel Thomas Harrison ,  Christopher Anthony Kemp ,  Michael A. Salem

IPC: G06V20/62 ,  G06V30/413 ,  G06V30/19 ,  G06V30/10

CPC classification number: G06V20/63 ,  G06V30/19173 ,  G06V30/413 ,  G06V30/10

Abstract: A system performs optical character recognition (OCR) on an image displaying a portion of an object. An image classification system identifies the object in the image, based on which one or more object detection models identify labels associated with the object within the image. The system determines text of the identified labels using OCR, and analyzes the OCR resultant text for discrepancies and/or inaccuracies. In response to identifying a discrepancy, the system provides a recommendation for improving the accuracy of the OCR resultant text.

公开(公告)号：US20210326589A1

公开(公告)日：2021-10-21

申请号：US17364343

申请日：2021-06-30

Applicant: salesforce.com, inc.

Inventor： Dennis Schultz ,  Daniel Thomas Harrison ,  Christopher Anthony Kemp ,  Michael A. Salem

IPC: G06K9/00 ,  G06K9/20

Abstract: A system performs optical character recognition (OCR) on an image displaying a portion of an object. An image classification system identifies the object in the image, based on which one or more object detection models identify labels associated with the object within the image. The system determines text of the identified labels using OCR, and analyzes the OCR resultant text for discrepancies and/or inaccuracies. In response to identifying a discrepancy, the system provides a recommendation for improving the accuracy of the OCR resultant text.

公开(公告)号：US11100319B2

公开(公告)日：2021-08-24

申请号：US16773813

申请日：2020-01-27

Applicant: salesforce.com, inc.

Inventor： Dennis Schultz ,  Daniel Thomas Harrison ,  Christopher Anthony Kemp ,  Michael A. Salem

IPC: G06K9/00 ,  G06K9/20

Abstract: A system performs optical character recognition (OCR) on an image displaying a portion of an object. An image classification system identifies the object in the image, based on which one or more object detection models identify labels associated with the object within the image. The system determines text of the identified labels using OCR, and analyzes the OCR resultant text for discrepancies and/or inaccuracies. In response to identifying a discrepancy, the system provides a recommendation for improving the accuracy of the OCR resultant text.

公开(公告)号：US20210232814A1

公开(公告)日：2021-07-29

申请号：US16773813

申请日：2020-01-27

Applicant: salesforce.com, inc.

Inventor： Dennis Schultz ,  Daniel Thomas Harrison ,  Christopher Anthony Kemp ,  Michael A. Salem

IPC: G06K9/00 ,  G06K9/20

Abstract: A system performs optical character recognition (OCR) on an image displaying a portion of an object. An image classification system identifies the object in the image, based on which one or more object detection models identify labels associated with the object within the image. The system determines text of the identified labels using OCR, and analyzes the OCR resultant text for discrepancies and/or inaccuracies. In response to identifying a discrepancy, the system provides a recommendation for improving the accuracy of the OCR resultant text.