-
公开(公告)号：US11887070B2
公开(公告)日：2024-01-30
申请号：US18058408
申请日：2022-11-23
Applicant: GROUPON, INC.
Inventor： Stephen Clark Mitchell , Pavel Melnichuk
CPC classification number: G06Q20/047 , G06V30/40 , G06F18/285 , G06V30/10 , G06V30/19113 , G06V2201/09
Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.
-
Patent Agency Ranking
公开(公告)号：US20230162165A1
公开(公告)日：2023-05-25
申请号：US18058408
申请日：2022-11-23
Applicant: GROUPON, INC.
Inventor： Stephen Clark Mitchell , Pavel Melnichuk
CPC classification number: G06Q20/047 , G06V30/40 , G06V30/10
Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.
-
公开(公告)号：US11538263B2
公开(公告)日：2022-12-27
申请号：US17115447
申请日：2020-12-08
Applicant: Groupon, Inc.
Inventor： Stephen Clark Mitchell , Pavel Melnichuk
Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.
-
公开(公告)号：US10891474B1
公开(公告)日：2021-01-12
申请号：US16254040
申请日：2019-01-22
Applicant: Groupon, Inc.
Inventor： Stephen Clark Mitchell , Pavel Melnichuk
Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.
-
公开(公告)号：US20240177123A1
公开(公告)日：2024-05-30
申请号：US18533584
申请日：2023-12-08
Applicant: GROUPON, INC.
Inventor： Stephen Clark Mitchell , Pavel Melnichuk
CPC classification number: G06Q20/047 , G06V30/40 , G06F18/285 , G06V30/10 , G06V30/19113 , G06V2201/09
Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.
-
公开(公告)号：US10229314B1
公开(公告)日：2019-03-12
申请号：US15281517
申请日：2016-09-30
Applicant: Groupon, Inc.
Inventor： Stephen Clark Mitchell , Pavel Melnichuk
Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.
-
-
-
-
-
Search Results
6
records
(took 0.035 seconds)
