Document Assembly Object Generation

1 . A method comprising:

obtaining, using one or more processors, a set of labels describing a document;

obtaining, using one or more processors, one or more images of the document, wherein the document in the one or more images are valid samples of the document;

identify, using the one or more processors, a set of document components based on document issuer provided information and a set of direct checks;

deriving, using the one or more processors, a set of document features based at least in part on the one or more images of the document and a set of derived checks; and

generating, using the one or more processors, a document assembly object describing valid instances of the document including the set of document components, the set of derived document features and a set of verification checks including the set of direct checks and the set of derived checks.

2 . The method of claim 1 , wherein the set of labels includes one or more of a main document type, a sub-type, a country, a state, a year of first issuing, and a version.

3 . The method of claim 1 , wherein the set of labels are concatenated to generate a unique identifier for the document assembly object describing valid instances of the document.

4 . The method of claim 1 , wherein obtaining the one or more images includes obtaining multiple images of a single instance of the valid document, the method further comprising:

generating a composite document image including a representation of an optically dynamic security feature present in valid instances of the document.

5 . The method of claim 1 , the method further comprising:

performing edge detection on at least one of the one or more images of the document; and

wherein deriving the set of document features based at least in part on the one or more images of the document includes:

analyzing an output of the edge detection for one or more of a presence and location of a watermark.

6 . The method of claim 1 , wherein:

obtaining the one or more images includes obtaining multiple images of different instances of a common, valid document;

deriving the set of document features based at least in part on the one or more images of the document includes performing object detection, thereby generating bounding boxes around detected objects; and

the document assembly object describing valid instances of the document includes information describing one or more of generated bounding boxes.

7 . The method of claim 6 , wherein:

the object detection includes optical character recognition;

the optical character recognition generates a bounding box around a set of text and an identification of one or more of font, font size, font color, font orientation, capitalization scheme, and font style,

the document assembly object includes a size and a position of the bounding box and the identification of one or more of the font, the font size, the font color, the font orientation, capitalization scheme, and the font style, and

the verification checks include verifying that a corresponding bounding box in a document image under test has one or more of the same relative position size, the same size, the same font, the same font size, the font orientation, capitalization scheme, and the same font style.

8 . The method of claim 1 , wherein deriving the set of document features based at least in part on the one or more images of the document includes one or more of:

a position of a first bounding box within the document or relative to a second bounding box;

an intra-bounding box feature; and

an inter-bounding box relationship, wherein the inter-bounding box relationship indicates areas of interest in two or more bounding boxes that include consistent information.

9 . The method of claim 1 , wherein deriving the set of document features based at least in part on the one or more images of the document includes reconstructing a background or microprinting.

10 . 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.

11 . The method of claim 1 , wherein identifying the set of document components based on document issuer provided information includes:

accessing an electronic version of the document issuer provided information;

automatically parsing the electronic version of the document issuer provided information; and

automatically extracting the set of document components from the document issuer provided information.

12 . A system comprising:

a processor; and

a memory, the memory storing instructions that, when executed by the processor, cause the system to:

obtain a set of labels describing a document;

obtain one or more images of the document, wherein the document in the one or more images are valid samples of the document;

identify a set of document components based on document issuer provided information and a set of direct checks;

derive a set of document features based at least in part on the one or more images of the document and a set of derived checks; and

generate a document assembly object describing valid instances of the document including the set of document components, the set of derived document features and a set of verification checks including the set of direct checks and the set of derived checks.

13 . The system of claim 12 , wherein obtaining the one or more images includes obtaining multiple images of a single instance of the valid document, and the memory further stores instructions that, when executed by the processor, cause the system to:

generate a composite document image including a representation of an optically dynamic security feature present in valid instances of the document.

14 . The system of claim 12 , the memory further stores instructions that, when executed by the processor, cause the system to:

perform edge detection on at least one of the one or more images of the document; and

wherein deriving the set of document features based at least in part on the one or more images of the document includes:

analyzing an output of the edge detection for one or more of a presence and location of a watermark.

15 . The system of claim 12 , wherein:

obtaining the one or more images includes obtaining multiple images of different instances of a common, valid document;

deriving the set of document features based at least in part on the one or more images of the document includes performing object detection, thereby generating bounding boxes around detected objects; and

the document assembly object describing valid instances of the document includes information describing one or more of generated bounding boxes.

16 . The method of claim 15 , wherein:

the object detection includes optical character recognition;

the optical character recognition generates a bounding box around a set of text and an identification of one or more of font, font size, font color, font orientation, capitalization scheme, and font style,

the document assembly object includes a size and a position of the bounding box and the identification of one or more of the font, the font size, the font color, the font orientation, capitalization scheme, and the font style, and

the verification checks include verifying that a corresponding bounding box in a document image under test has one or more of the same relative position size, the same size, the same font, the same font size, the font orientation, capitalization scheme, and the same font style.

17 . The system of claim 12 , wherein deriving the set of document features based at least in part on the one or more images of the document includes one or more of:

a position of a first bounding box within the document or relative to a second bounding box;

an intra-bounding box feature; and

an inter-bounding box relationship, wherein the inter-bounding box relationship indicates areas of interest in two or more bounding boxes that include consistent information.

18 . The system of claim 12 , wherein deriving the set of document features based at least in part on the one or more images of the document includes reconstructing a background or microprinting.

19 . The system of claim 12 , wherein the document components include one or more of mandatory fields, optional fields, example images, security features, and document layout.

20 . The system of claim 12 , wherein identifying the set of document components based on document issuer provided information includes:

accessing an electronic version of the document issuer provided information;

automatically parsing the electronic version of the document issuer provided information; and

automatically extracting the set of document components from the document issuer provided information.