# US 2021/0264556 A1 · Automatically attaching optical character recognition data to images

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0264556 A1
- Document ID: US20210264556A1
- Status: Published application
- Kind: A1
- Application number: 17/317,094
- Filed: 2021-05-11
- Published: 2021-08-26
- Earliest claimed: 2017-12-05
- Assignees: LendingClub Corporation
- Applicants: LendingClub Corporation
- Inventors: Aaron Brown; Samantha Puth
- Web page: https://patentgrep.com/patent/US20210264556A1

## CPC

- G06V 30/416: Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
- G06T 1/0021: {Image watermarking}
- G06T 2201/0062: Embedding of the watermark in text images, e.g. watermarking text documents using letter skew, letter distance or row distance
- G06T 2201/0065: Extraction of an embedded watermark; Reliable detection
- G06V 30/10: Character recognition
- G06V 2201/10: Recognition assisted with metadata
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Techniques for automatically attaching optical character recognition data to images are provided. The techniques include receiving an image file containing an image and performing optical character recognition on the image to generate text output. The techniques then continue by identifying a particular text item from within the generated text output and determining that the particular text item is a value for particular corresponding key. Then metadata that indicates that the particular text item is a value for the particular key is stored in the image file.

## Claims

### Claim 1

A method comprising:
receiving an image file containing an image;
performing optical character recognition on the image to extract text output from the image;
within the text output, identifying a particular text item;
wherein the particular text item is located at a particular location of the image;
based at least in part on the image, automatically determining that the particular text item is a value for a particular key;
generating metadata (a) that includes the particular text item and (b) that indicates that the particular text item is a value for the particular key; and
creating an updated image file by inserting, within the image file, the metadata; and
based, at least in part, on the particular location, displaying the particular text item as rendered text within a display of the image;
wherein the method is performed using one or more computing devices.

### Claim 2 (depends on 1)

The method of claim 1, wherein the rendered text is displayed in a user interface, the method further comprising:
receiving, via the user interface, an edited version of the particular text item; and
storing, in the metadata, the edited version of the particular text item.

### Claim 3 (depends on 2)

The method of claim 2, wherein the edited version of the particular text item is stored, in the metadata, as a corrected version of the value for the particular key; and wherein the particular text item is stored, in the metadata, as a previous version of the value for the particular key.

### Claim 4 (depends on 1)

The method of claim 1, wherein the rendered text is displayed at the particular location, within the image, that corresponds to the particular text item.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving an interaction event from a user interface; and
in response to receiving the interaction event, ceasing to display the rendered text within the display of the image.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
receiving a second interaction event from the user interface; and
in response to receiving the second interaction event, displaying the rendered text within the display of the image.

### Claim 7 (depends on 1)

The method of claim 1, wherein a representation of the particular text item at the particular location of the image is obscured.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
receiving an interaction event from a user interface; and
in response to receiving the interaction event from the user interface, ceasing to obscure the representation of the particular text item at the particular location of the image.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
detecting a font type and/or a size of a representation of the particular text item in the image;
wherein the rendered text matches the font type and or size.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
displaying, in a user interface, a form that includes a particular editable text box that is visually associated with a label for the particular key; and
populating the particular editable text box with the particular text item.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
receiving, via the particular editable text box in the user interface, a corrected text item associated with the particular key;
generating second metadata (a) that includes the corrected text item and (b) that indicates that the corrected text item is a value for the particular key; and
inserting, within the image file, the second metadata.

### Claim 12 (depends on 10)

The method of claim 10, further comprising:
within the text output, identifying a second text item;
based at least in part on the image, automatically determining that the second text item is a value for a second key;
wherein the form includes a second editable text box that is visually associated with a label for the second key; and
populating the second editable text box with the second text item.

### Claim 13 (depends on 1)

The method of claim 1, wherein automatically determining that the particular text item is a value for the particular key is based, at least in part, on the particular location of the particular text item.

### Claim 14 (depends on 13)

The method of claim 13, wherein automatically determining that the particular text item is a value for the particular key is further based, at least in part, on the image being of a particular document type.

### Claim 15 (depends on 1)

The method of claim 1, further comprising:
within the text output, identifying a particular label that corresponds to the particular key;
wherein the metadata stored within the updated image file associates the particular text item with the particular label.

### Claim 16 (depends on 1)

The method of claim 1, further comprising:
within the text output, identifying a particular label that corresponds to the particular key;
determining a second location, within the image, that corresponds to the particular label;
wherein automatically determining that the particular text item is a value for the particular key is based, at least in part, on the particular location and the second location.

### Claim 17 (depends on 1)

The method of claim 1, wherein:
the image is associated with a particular entity;
a row in a database table is associated with the particular entity; and
the metadata further comprises data that associates the image file with the row of the database table.

### Claim 18 (depends on 1)

The method of claim 1, further comprising:
within the text output, identifying a second text item;
based at least in part on the image, automatically determining that the second text item is a value for a second key;
wherein the metadata further includes the second text item and indicates that the second text item is a value for the second key;
wherein the second key is different than the particular key.

### Claim 19

One or more non-transitory computer-readable media storing instructions that, when executed by one or more computing devices, cause:
receiving an image file containing an image;
performing optical character recognition on the image to extract text output from the image;
within the text output, identifying a particular text item;
wherein the particular text item is located at a particular location of the image;
based at least in part on the image, automatically determining that the particular text item is a value for a particular key;
generating metadata (a) that includes the particular text item and (b) that indicates that the particular text item is a value for the particular key; and
creating an updated image file by inserting, within the image file, the metadata; and
based, at least in part, on the particular location, displaying the particular text item as rendered text within a display of the image.

### Claim 20

A system, comprising one or more computing devices, and one or more non-transitory computer-readable media storing instructions that, when executed by the one or more computing devices, cause:
receiving an image file containing an image;
performing optical character recognition on the image to extract text output from the image;
within the text output, identifying a particular text item;
wherein the particular text item is located at a particular location of the image;
based at least in part on the image, automatically determining that the particular text item is a value for a particular key;
generating metadata (a) that includes the particular text item and (b) that indicates that the particular text item is a value for the particular key; and
creating an updated image file by inserting, within the image file, the metadata; and
based, at least in part, on the particular location, displaying the particular text item as rendered text within a display of the image.
