# US 10,489,645 B2 · System and method for automatic detection and verification of optical character recognition data

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

- Number: US 10,489,645 B2
- Document ID: US10489645B2
- Status: Granted
- Kind: B2
- Application number: 15/922,821
- Filed: 2018-03-15
- Published: 2019-09-19
- Granted: 2019-11-26
- Earliest claimed: 2018-03-15
- Assignees: SurePrep, LLC
- Applicants: Sureprep, LLC
- Inventors: David Wyle; Srinivas Lingineni; Will Hosek
- Web page: https://patentgrep.com/patent/US10489645B2

## CPC

- G06V 30/127: {with the intervention of an operator}
- G06T 7/13: Edge detection
- G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
- G06V 30/418: Document matching, e.g. of document images
- G06T 2207/30176: Document
- G06V 30/10: Character recognition
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Methods for automatically verifying text detected by optical character recognition (OCR). The method includes obtaining a native digital document having an image layer comprising a matrix of computer-renderable pixels and a text layer comprising computer-readable encodings of a sequence of characters. The method includes obtaining OCR-detected text from the image layer of the native digital document and a pixel-based coordinate location of the OCR-detected text in the image layer of the native digital document. The method includes determining, using a pixel transformation, a computer-interpretable location of the OCR-detected text in the text layer of the native digital document. The method includes detecting text in the text layer based on the computer-interpretable location of the OCR-detected text in the text layer. The method includes rendering only the detected text in the text layer when the OCR-detected text does not match the detected text in the text layer.

## Claims

### Claim 1

A method for automatically verifying text detected by optical character recognition (OCR), the method comprising:
obtaining a native digital document having an image layer comprising a matrix of computer-renderable pixels and a text layer comprising computer-readable encodings of a sequence of characters;
obtaining an OCR-detected text from the image layer of the native digital document and a pixel-based coordinate location of the OCR-detected text in the image layer of the native digital document;
determining, using a pixel transformation, a computer-interpretable location of the OCR-detected text in the text layer of the native digital document based on the pixel-based coordinate location of the OCR-detected text in the image layer of the native digital document;
applying the computer-interpretable location of the OCR-detected text to the text layer of the native digital document to detect text in the text layer corresponding to the OCR-detected text; and
rendering only the detected text in the text layer as an output when the OCR-detected text does not match the detected text in the text layer, to improve accuracy of the output text.

### Claim 2 (depends on 1)

The method of claim 1, wherein the OCR-detected text and the pixel-based coordinate location of the OCR-detected text in the image layer is determined by an optical character recognition device executing optical character recognition computer software.

### Claim 3 (depends on 1)

The method of claim 1, wherein the pixel-based coordinate location of the OCR-detected text in the image layer is associated with a four-sided box surrounding the OCR-detected text, the four-sided box having a left side, a top side, a right side, and a bottom side.

### Claim 4 (depends on 3)

The method of claim 3, wherein the pixel-based coordinate location of the OCR-detected text in the image layer includes a left value corresponding to a distance from a left edge of the native digital document to the left side of the four-sided box, a top value corresponding to a distance from the top edge of the native digital document to the top side of the four-sided box, a right value corresponding to a distance from the left edge of the native digital document to the right side of the four-sided box, and a bottom value corresponding to a distance from the top edge of the native digital document to the bottom side of the four-sided box.

### Claim 5 (depends on 1)

The method of claim 1, further comprising providing a display of the image layer of the native digital document and a confirmatory indicator adjacent to the location of the OCR-detected text when the OCR-detected text matches the detected text in the text layer or a non-confirmatory indicator adjacent to the location of the OCR-detected text when the OCR-detected text does not match the detected text in the text layer.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
determining, for each text of the native digital document, whether an OCR-detected text for each text matches a corresponding text in the text layer, and
providing, on the display, a respective confirmatory indicator for each text where the OCR-detected text matches the corresponding text in the text layer, and a respective non-confirmatory indicator for each text where the OCR-detected text does not match the corresponding text in the text layer,
wherein the display is limited to a single page of a display screen.

### Claim 7 (depends on 5)

The method of claim 5, further comprising receiving, in real-time from the user via an input unit, a correction for the OCR-detected text when the OCR-detected text does not match the detected text in the text layer.

### Claim 8 (depends on 1)

The method of claim 1, wherein the native digital document is obtained by receiving the native digital document from a user device of the user, by receiving the native digital document from a third-party server, or by retrieving the native digital document from the third-party server.

### Claim 9 (depends on 1)

The method of claim 1, further comprising discarding or deleting the OCR-detected text when the OCR-detected text does not match the detected text in the text layer.

### Claim 10 (depends on 1)

The method of claim 1, further comprising automatically outputting, to a computer software, the detected text in the text layer to improve accuracy of text extraction from the native digital document.

### Claim 11

A system for automatically verifying text detected by optical character recognition (OCR), the system comprising:
an optical character recognition device configured to:
receive a native digital document having an image layer comprising a matrix of computer-renderable pixels and a text layer comprising computer-readable encodings of a sequence of characters, and
use optical character recognition software to detect text from the image layer of the native digital document and a pixel-based coordinate location of the OCR-detected text in the image layer of the native digital document;
a verification device configured to:
determine, using a pixel transformation, a computer-interpretable location of the OCR-detected text in the text layer of the native digital document based on the pixel-based coordinate location of the OCR-detected text in the image layer of the native digital document, and
apply the computer-interpretable location of the OCR-detected text to the text layer of the native digital document to detect text in the text layer corresponding to the OCR-detected text; and
an output device configured to render only the detected text in the text layer as an output when the OCR-detected text does not match the detected text in the text layer, to improve accuracy of the output text.

### Claim 12 (depends on 11)

The system of claim 11, wherein the OCR-detected text and the pixel-based coordinate location of the OCR-detected text in the image layer is determined by an optical character recognition device executing optical character recognition computer software.

### Claim 13 (depends on 12)

The system of claim 12, further comprising a correction device connected to the verification device and configured to receive, in real-time from the user via an input unit, a correction for the OCR-detected text when the OCR-detected text does not match the detected text in the text layer.

### Claim 14 (depends on 11)

The system of claim 11, wherein the pixel-based coordinate location of the OCR-detected text in the image layer is associated with a four-sided box surrounding the OCR-detected text, the four-sided box having a left side, a top side, a right side, and a bottom side.

### Claim 15 (depends on 14)

The system of claim 14, wherein the pixel-based coordinate location of the OCR-detected text in the image layer includes a left value corresponding to a distance from a left edge of the native digital document to the left side of the four-sided box, a top value corresponding to a distance from the top edge of the native digital document to the top side of the four-sided box, a right value corresponding to a distance from the left edge of the native digital document to the right side of the four-sided box, and a bottom value corresponding to a distance from the top edge of the native digital document to the bottom side of the four-sided box.

### Claim 16 (depends on 11)

The system of claim 11, wherein the output device is further configured to provide a display of the image layer of the native digital document and a confirmatory indicator adjacent to the location of the OCR-detected text when the OCR-detected text matches the detected text in the text layer or a non-confirmatory indicator adjacent to the location of the OCR-detected text when the OCR-detected text does not match the detected text in the text layer.

### Claim 17 (depends on 16)

The system of claim 16, wherein the verification device is further configured to determine, for each text of the native digital document, whether an OCR-detected text for each text matches a corresponding text in the text layer,
wherein the output device is further configured to provide, on the display, a respective confirmatory indicator for each text where the OCR-detected text matches the corresponding text in the text layer, and a respective non-confirmatory indicator for each text where the OCR-detected text does not match the corresponding text in the text layer, and
wherein the display is limited to a single page of a display screen.

### Claim 18 (depends on 11)

The system of claim 11, wherein the native digital document is received from a user device of the user, received from a third-party server, or retrieved from the third-party server.

### Claim 19 (depends on 11)

The system of claim 11, wherein the verification device is further configured to discard or delete the OCR-detected text when the OCR-detected text does not match the detected text in the text layer.

### Claim 20 (depends on 11)

The system of claim 11, wherein the verification device is further configured to automatically output, to a computer software, the detected text in the text layer to improve accuracy of text extraction from the native digital document.
