# US 2021/0263597 A1 · Recovering perspective distortions

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

- Number: US 2021/0263597 A1
- Document ID: US20210263597A1
- Status: Published application
- Kind: A1
- Application number: 17/056,442
- Filed: 2018-10-31
- Published: 2021-08-26
- Earliest claimed: 2018-10-31
- Assignees: Hewlett-Packard Development Company, L.P.
- Applicants: Hewlett-Packard Development Company, L.P.
- Inventors: Stephen Pollard
- Web page: https://patentgrep.com/patent/US20210263597A1

## CPC

- G06T 7/593: from stereo images
- G06F 3/0317: {in co-operation with a patterned surface, e.g. absolute position or relative movement detection for an optical mouse or pen positioned with respect to a coded surface}
- G06F 3/0321: {by optically sensing the absolute position with respect to a regularly patterned surface forming a passive digitiser, e.g. pen optically detecting position indicative tags printed on a paper sheet (constructional details of pen-shaped pointing devices G06F3/03545, G06F3/03542, G06F3/037)}
- G06F 3/03545: {Pens or stylus}
- G06F 3/0383: {Signal control means within the pointing device}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06T 7/187: involving region growing; involving region merging; involving connected component labelling
- H04N 13/207: using a single two-dimensional [2D] image sensor
- H04N 13/239: using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence)
- H04N 23/56: provided with illuminating means
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A method for recovering perspective distortion of a coded dot pattern on a surface, comprises generating a stereo-pair of images of a portion of the coded dot pattern, the stereo-pair of images comprising an overlap region comprising a subset of dots of the coded dot pattern that are common to the stereo-pair of images, selecting, in one image of the stereo-pair of images, a focus pattern from the subset of dots, determining a set of potential matches for the focus pattern in the other image of the stereo-pair of images, for each potential match, determining a set of additional dots of the coded dot pattern consistent with a single plane, and selecting a single plane with the highest number of consistent matched dots.

## Claims

### Claim 1

A method for recovering perspective distortion of a coded dot pattern on a surface, comprising:
generating a stereo-pair of images of a portion of the coded dot pattern, the stereo-pair of images comprising an overlap region comprising a subset of dots of the coded dot pattern that are common to the stereo-pair of images;
selecting, in one image of the stereo-pair of images, a focus pattern from the subset of dots;
determining a set of potential matches for the focus pattern in the other image of the stereo-pair of images;
for each potential match, determining a set of additional dots of the coded dot pattern consistent with a single plane; and
selecting a single plane with the highest number of consistent matched dots.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein determining a set of potential matches for the focus pattern further comprises:
using a set of dots within a predetermined region around the focus pattern.

### Claim 3 (depends on 2)

The method as claimed in claim 2, further comprising:
iteratively growing the predetermined region to encompass an increasing neighbourhood of dots.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein determining the set of potential matches for the focus pattern in the other image of the stereo-pair of images further comprises:
selecting multiple dots falling along a horizontal epipolar line projected, in the other image, at a vertical position corresponding to the vertical position of the focus pattern.

### Claim 5

Apparatus, comprising:
an image sensor structure to generate a pair of images of a portion of a coded pattern on a surface; and a processor to:
select, in one image of the pair of images, a focus pattern present in an overlap region of the of pair images; and
determine a set of additional points of the coded pattern consistent with a single plane and based around a set of potential matches for the focus pattern.

### Claim 6 (depends on 5)

The apparatus as claimed in claim 5, wherein the image sensor structure comprises a single image sensor to capture the pair images of the portion.

### Claim 7 (depends on 5)

The apparatus as claimed in claim 5, wherein the image sensor structure comprises a pair of image sensors to capture respective ones of the pair images of the portion.

### Claim 8 (depends on 7)

The apparatus as claimed in claim 7, wherein the pair of images sensors are disposed on generally opposite sides of the apparatus.

### Claim 9 (depends on 5)

The apparatus as claimed in claim 5, further comprising a source of near infra-red radiation to illuminate the surface.

### Claim 10 (depends on 6)

The apparatus as claimed in claim 6, the processor to use two overlapping regions of the image sensor to generate the pair of images.

### Claim 11 (depends on 5)

The apparatus as claimed in claim 5, further comprising a prism or semi-reflective mirror to reflect a portion of the coded pattern on the surface to the image sensor structure.

### Claim 12 (depends on 5)

The apparatus as claimed in claim 5, wherein the apparatus is an optoelectronic pen comprising a nib, the processor to select the focus pattern from a region of the coded pattern in the vicinity of the nib.

### Claim 13

A non-transitory machine-readable storage medium encoded with instructions executable by a processor, to:
select a focus pattern from a subset of points within an overlapping region of a pair of images of a coded pattern;
generate a set of potential matches for the focus pattern in one of the images;
compare the disposition of elements of the coded pattern around respective ones of the potential matches with a corresponding disposition of elements of the coded pattern in a predetermined area around the focus pattern in the other of the pair of images; and
select one of the potential matches with a largest number of elements of the coded pattern matching those within the predetermined area around the focus pattern.

### Claim 14 (depends on 13)

The non-transitory machine-readable storage medium of claim 13, further encoded with instructions executable by a processor, to:
iteratively enlarge the predetermined region to encompass an increasing neighbourhood of elements around the focus pattern.

### Claim 15 (depends on 13)

The non-transitory machine-readable storage medium of claim 13, further encoded with instructions executable by a processor, to:
select a single plane with the highest number of consistent matched dots.
