# US 2013/0156344 A1 · Multi-perpendicular line-based deskew with affine and perspective distortion correction

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

- Number: US 2013/0156344 A1
- Document ID: US20130156344A1
- Status: Published application
- Kind: A1
- Application number: 13/325,396
- Filed: 2011-12-14
- Published: 2013-06-20
- Earliest claimed: 2011-12-14
- Assignees: Ancestry.com
- Inventors: Jack Reese; Shawn Reid
- Web page: https://patentgrep.com/patent/US20130156344A1

## CPC

- H04N 1/3878: {Skew detection or correction}
- G06T 3/608: by skew deformation, e.g. two-pass or three-pass rotation
- G06T 5/80: Geometric correction
- G06V 10/243: {by compensating for image skew or non-uniform image deformations}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The present invention provides a method of correcting alignment of an image. The method includes identifying an image of a document, and detecting a plurality of lines within the image. The method also includes classifying at least a subset of the plurality of lines as either horizontal or vertical lines, and determining whether a variance exists within a subset of the plurality of lines. Furthermore, the method includes applying a corrective transformation to adjust the image, where the variance within the subset of the plurality of lines is at least partially reduced as compared to the variance prior to the application of the corrective transformation.

## Claims

### Claim 1

A method of correcting alignment of an image, the method comprising:
identifying an image of a document;
detecting a plurality of lines within the image;
classifying at least a subset of the plurality of lines as horizontal lines or vertical lines;
determining that a variance exists within the subset of the plurality of lines; and
applying a corrective transformation to adjust the image, wherein the variance within the subset of the plurality of lines is at least partially reduced as compared to the variance prior to the application of the corrective transformation.

### Claim 2 (depends on 1)

The method of correcting alignment of an image as in claim 1, wherein the variance that exists within the subset of the plurality of the lines is between at least two horizontal lines, and the variance comprises an angle of deviation that exists between the at least two horizontal lines as compared to being parallel to one another.

### Claim 3 (depends on 1)

The method of correcting alignment of an image as in claim 1, wherein the variance that exists within the subset of the plurality of the lines is between at least two vertical lines, and the variance comprises an angle of deviation that exists between the at least two vertical lines as compared to being parallel to one another.

### Claim 4 (depends on 1)

The method of correcting alignment of an image as in claim 1, wherein the variance comprises horizontal or vertical perspective foreshortening.

### Claim 5 (depends on 1)

The method of correcting alignment of an image as in claim 1, wherein the variance that exists within the subset of the plurality of the lines is between at least one horizontal line and at least one vertical line, and the variance comprises the intersection of the lines being at an angle other than perpendicular to each other.

### Claim 6 (depends on 5)

The method of correcting alignment of an image as in claim 5, wherein the variance comprises skew or shear distortion.

### Claim 7 (depends on 1)

The method of correcting alignment of an image as in claim 1, further comprising after applying the corrective transformation:
determining that the adjusted image orientation is at an angle other than the orientation of a reference set of axes; and
rotating the adjusted image to equalize the orientation of the adjusted image with the reference set of axes.

### Claim 8 (depends on 1)

The method of correcting alignment of an image as in claim 1, wherein the identification of the image occurs at a computer imaging device that processes the image identified, stores the image, and retrieves the image prior to detecting the plurality of lines within the image.

### Claim 9 (depends on 1)

The method of correcting alignment of an image as in claim 1, wherein the image is a computer readable image.

### Claim 10 (depends on 9)

The method of correcting alignment of an image as in claim 9, further comprising generating the computer readable image with a document imaging system that captures the image of a document.

### Claim 11 (depends on 10)

The method of correcting alignment of an image as in claim 10, wherein the document imaging system comprises at least one of microfilm, microfiche, an on demand printer, a facsimile machine, a copier, a document scanner, or a multifunction printer.

### Claim 12 (depends on 1)

The method of claim 1, wherein the document comprises at least one of a table, a grid, or another detectable line-based aspect of the image.

### Claim 13

A method of correcting skew in an image containing line-based features, the method comprising:
identifying a skewed image;
detecting multiple lines within the image;
classifying at least a subset of the multiple lines as horizontal lines, vertical lines, or a combination of horizontal and vertical lines;
determining that at least one line is distorted, wherein the line deviates from the axis of symmetry of the line in at least one segment along the line; and
applying a truing application to the image to adjust the at least one line that is distorted to be reformed along the axis of symmetry of the line to deskew the image.

### Claim 14 (depends on 13)

The method of correcting skew in an image as in claim 13, wherein the classifying of the at least a subset of the plurality of lines analyses the entirety of the detected lines to determine the line classification, and wherein the classification comprises a horizontal or vertical determination.

### Claim 15 (depends on 13)

The method of correcting skew in an image as in claim 13, wherein the determination compares the lines to other lines in the image to determine type and extent of skewing.

### Claim 16 (depends on 13)

The method of claim 13, wherein the classifying is at least in part based on a comparative orientation of at least two lines, including whether the at least two lines are parallel or perpendicular to each other.

### Claim 17 (depends on 16)

The method of claim 16, wherein the parallelism of the at least two lines is determined within a range, wherein the determination of parallelism within the range comprises classifying the at least two lines as parallel despite the at least two lines being other than equidistant at all points along the at least two lines.

### Claim 18 (depends on 16)

The method of claim 16, wherein at least one horizontal and at least one vertical line are determined to be perpendicular based on a range, wherein the determination within the range comprises classifying the at least one horizontal and at least one vertical line as perpendicular despite that the angle between the at least one horizontal and at least one vertical line may be greater than or less than ninety degrees.

### Claim 19 (depends on 13)

The method of claim 13, wherein the truing application is configured to model the image to determine how the image is to be adjusted.

### Claim 20

A computer-readable medium having sets of instructions stored thereon, which when executed by a computer cause the computer to:
identify an image of a document;
detect a plurality of lines within the image;
classify at least a subset of the plurality of lines as horizontal lines or vertical lines;
determine that a variance exists within the subset of the plurality of lines; and
apply a corrective transformation to adjust the image, wherein the variance within the subset of the plurality of lines is at least partially reduced as compared to the variance prior to the application of the corrective transformation.
