Document assembly object generation and use in document image verification

Patent metadata

Field	Value
Publication number	US-12573226-B2
Application number	US-202218148544-A
Country	US
Kind code	B2
Filing date	Dec 30, 2022
Priority date	Dec 30, 2022
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

The disclosure includes a system and method for obtaining a query including a document assembly object identifier, the query associated with a request to verify a document under test present in an image; obtaining a document assembly object describing a valid document uniquely associated with the identifier, the document assembly object including: a set of document components, a set of derived document features, and a set of verification checks including one or more of a direct check and a derived check; obtaining aggregated context information associated with the document under test; and sending the document assembly object and aggregated context information for use in verification of the document under test.

First claim

What is claimed is:

1 . A method comprising:
deriving, using one or more processors, a set of derived document features based on a set of valid document instances; determining, using the one or more processors, a set of verification checks based on one or more of information published by a document issuer, and the set of derived document features; generating, using the one or more processors, a document assembly object describing a valid document and uniquely associated with a document assembly object identifier, the document assembly object including:
a set of document components,
the set of derived document features, and
the set of verification checks including one or more of a direct check and a derived check;
obtaining, using the one or more processors, a query associated with a request to verify a document under test present in an image, the query including the document assembly object identifier associated with the document assembly object; obtaining, using the one or more processors, aggregated context information associated with the document under test; and outputting, using the one or more processors, a decision whether the document under test is valid based on the set of verification checks and the aggregated context information.

2 . The method of claim 1 , wherein the unique document assembly object identifier is a concatenation of one or more of a main document type, a sub-type, a country, a state, a year of first issuing, and a version associated with the document under test.

3 . The method of claim 1 , wherein the unique document assembly object identifier is received from a document classifier, and the unique document assembly object identifier is based on a classification of the document under test.

4 . The method of claim 1 , wherein the document components include one or more of mandatory fields, optional fields, example images, security features, and document layout.

5 . The method of claim 1 , wherein the document assembly object includes a JavaScript Object Notation (JSON) object and at least one link to a valid sample snippet.

6 . The method of claim 1 , wherein the derived document features include a reconstruction of a background or microprinting.

7 . The method of claim 1 , wherein the set of verification checks includes at least one direct verification check extracted from document issuer provided information, the document issuer issuing valid instances of the document under test.

8 . The method of claim 1 , wherein the set of verification checks includes at least one derived verification check based on one or more of the derived document features.

9 . The method of claim 1 , wherein the set of derived document features includes a bounding box template, wherein each bounding box in the bounding box template is associated with text or an object present in a valid instance of the document and an expected location of the text or the object within the valid instance of the document.

10 . The method of claim 1 , wherein the aggregated context information includes a set of intermediary results associated with historic document evaluations.

11 . A system comprising:
a processor; and a memory, the memory storing instructions that, when executed by the processor, cause the system to: derive, a set of derived document features based on a set of valid document instances; determine, using a machine learning model, a set of verification checks based on one or more of information published by a document issuer, and the set of derived document features; generate a document assembly object describing a valid document and uniquely associated with a document assembly object identifier, the document assembly object including:
a set of document components,
the set of derived document features, and
the set of verification checks including one or more of a direct check and a derived check;
obtain, a query associated with a request to verify a document under test present in an image, the query including the document assembly object identifier associated with the document assembly object; obtain aggregated context information associated with the document under test; and output a decision whether the document under test is valid based on the set of verification checks and the aggregated context information.

12 . The system of claim 11 , wherein the unique document assembly object identifier is a concatenation of one or more of a main document type, a sub-type, a country, a state, a year of first issuing, and a version associated with the document under test.

13 . The system of claim 11 , wherein the unique document assembly object identifier is received from a document classifier, and the unique document assembly object identifier is based on a classification of the document under test.

14 . The system of claim 11 , wherein the document components include one or more of mandatory fields, optional fields, example images, security features, and document layout.

15 . The system of claim 11 , wherein the document assembly object includes a JavaScript Object Notation (JSON) object and at least one link to a valid sample snippet.

16 . The system of claim 11 , wherein the derived document features include a reconstruction of a background or microprinting.

17 . The system of claim 11 , wherein the set of verification checks includes at least one direct verification check extracted from document issuer provided information, the document issuer issuing valid instances of the document under test.

18 . The system of claim 11 , wherein the set of verification checks includes at least one derived verification check based on one or more of the derived document features.

19 . The system of claim 11 , wherein the set of derived document features includes a bounding box template, wherein each bounding box in the bounding box template is associated with text or an object present in a valid instance of the document and an expected location of the text or the object within the valid instance of the document.

20 . The system of claim 11 , wherein the aggregated context information includes a set of intermediary results associated with historic document evaluations.

Assignees

• Jumio Corp

Inventors

• Wells Stuart
• Balogh Attila
• Singh Anshuman Vikram
• Krump Thomas

Classifications

• G06V30/414

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title

• G06F16/53 Primary

  Querying · CPC title

• G06F16/55

  Clustering; Classification · CPC title

• G06V30/40

  Document-oriented image-based pattern recognition · CPC title

• G06V30/418

  Document matching, e.g. of document images · CPC title