# US 2020/0367590 A1 · Devices and methods for extracting body measurements from 2d images

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

- Number: US 2020/0367590 A1
- Document ID: US20200367590A1
- Status: Published application
- Kind: A1
- Application number: 16/636,992
- Filed: 2018-08-10
- Published: 2020-11-26
- Earliest claimed: 2017-08-11
- Assignees: North Carolina State University
- Applicants: North Carolina State University
- Inventors: Cynthia L. Istook; Andre J. West; Sibei Xia; Jiayin Li; James Beebe Hawes COLLIER
- Web page: https://patentgrep.com/patent/US20200367590A1

## CPC

- A61B 5/1072: {measuring distances on the body, e.g. measuring length, height or thickness (A61B5/1076 takes precedence)}
- A41H 1/02: Devices for taking measurements on the human body
- A41H 1/06: in combination with marking
- A61B 5/1079: {using optical or photographic means}
- G06V 10/225: {based on a marking or identifier characterising the area}
- G06V 10/754: {involving a deformation of the sample pattern or of the reference pattern; Elastic matching}
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06T 7/50: Depth or shape recovery
- G06T 2207/30196: Human being; Person
- G06T 2210/16: Cloth
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- A41H: APPLIANCES OR METHODS FOR MAKING CLOTHES, e.g. FOR DRESS-MAKING OR FOR TAILORING, NOT OTHERWISE PROVIDED FOR
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Various examples are provided for obtaining body measurements of a user, predicting body measurements of a user, and/or the like. Examples include a coded dimensioning garment having a stretchable fabric that conforms to a wearer's body without substantial compression or distortion of the skin. The garment can include measurement markings of known sizes at one or more known locations on the fabric. Methods are provided for predicting body measurements from a user. Image(s) of a user wearing the garment in a reference pose are captured and can be uploaded to a body measurement application. The real-world dimensions can be converted to pixel dimensions in the same ratio as the real world dimensions and inputted into a prediction model to generate measurements from areas of interest on the user.

## Claims

### Claim 1

A coded dimensioning garment, comprising:
a stretchable fabric that conforms to a wearer's body without substantial compression or distortion of skin of the wearer; and
measurement markings of known sizes disposed at known locations on the stretchable fabric.

### Claim 2 (depends on 1)

The coded dimensioning garment of claim 1, wherein the coded dimensioning garment is an item of clothing.

### Claim 3 (depends on 1)

The coded dimensioning garment of claim 1, wherein the coded dimensioning garment is a stretchable band.

### Claim 4 (depends on 1)

The coded dimensioning garment of claim 1, wherein the measurement markings are selected from colored bands, colored lines, areas of color gradients, areas of patterns, areas of motif, or a combination thereof.

### Claim 5 (depends on 1)

The coded dimensioning garment of claim 1, further comprising non-deformable reference markings secured to the stretchable fabric.

### Claim 6

A method for predicting body measurements from a user comprising:
capturing an image of a user wearing a coded dimensioning garment, wherein the coded dimensioning garment has one or more markings of known size and relationship to each other, and wherein the user is in at least one reference pose near a reference object of known dimensions in the image;
uploading at least one image of the user in the reference pose to an application;
forming a target image of the reference object in which the real world dimensions of the reference object are converted to pixel dimensions in the same ratio as the real world dimensions;
scaling and transforming the image of the user to match the target image to create a transformed user image;
measuring areas of interest on the user using the one or more markings on the dimensioning garment in the transformed user image to generate user's measurements; and
providing the user's measurements into a prediction model to generate predicted measurements.

### Claim 7 (depends on 6)

The method of claim 6, wherein the at least one image of the user includes a front photograph and a side photograph of the user in the reference pose.

### Claim 8 (depends on 6)

The method of claim 6, wherein data used to generate the prediction model includes anthropometric data, demographic information, weight, body mass index, height, manufacturer data, user preferences, or a combination thereof.

### Claim 9 (depends on 8)

The method of claim 8, further comprising obtaining additional user information provided by the user, the additional user information comprising demographic information, weight, body mass index, height, manufacturer data, user preferences, or a combination thereof.

### Claim 10 (depends on 6)

The method of claim 6, wherein the at least one dimensioning garment is an item of clothing.

### Claim 11 (depends on 6)

The method of claim 6, wherein the at least one dimensioning garment is a stretchable band.

### Claim 12 (depends on 6)

The method of claim 6, wherein the known dimensions of the reference object are provided by the user or are selected from a set of standard dimensions of predetermined objects.

### Claim 13 (depends on 6)

The method of claim 6, wherein the user's measurements are extrapolated manually from photographs.

### Claim 14 (depends on 6)

The method of claim 6, wherein the user's measurements are extracted using a computer executed program.

### Claim 15 (depends on 6)

The method of claim 6, further comprising requesting additional images from the user.

### Claim 16 (depends on 6)

The method of claim 6, further comprising providing the user with at least one error message if a problem is detected with at least one of the images of the user.

### Claim 16 (depends on 6)

The method of claim 6, wherein the reference object of known dimensions is a non-deformable reference marking adhered to the coded dimensioning garment.

### Claim 17 (depends on 16)

The method of claim 16, wherein the problem is selected from insufficient lighting, distortion of the image, non-detectable garment markings, measurements outside expected values, or a combination thereof.
