# US 2015/0103074 A1 · Method and apparatus for generating shape descriptor of a model

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

- Number: US 2015/0103074 A1
- Document ID: US20150103074A1
- Status: Published application
- Kind: A1
- Application number: 14/402,186
- Filed: 2012-05-22
- Published: 2015-04-16
- Earliest claimed: 2012-05-22
- Assignees: Thomson Licensing
- Inventors: Kangying Cai; Wei Liang Meng; Tao Luo
- Web page: https://patentgrep.com/patent/US20150103074A1

## CPC

- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 17/30: Polynomial surface description
- G06V 10/46: Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features (colour feature extraction G06V10/56)
- G06V 20/64: Three-dimensional [3D] objects
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The invention provides a method for generating an n dimensional vector as a shape descriptor of a model, and corresponding apparatus and shape descriptor. The method comprises: determining a type element of the vector to describe the basic shape of the model; and calculating n−1 metric elements of the vector, each of which represents the percentage of all of a feature of the model falling into one of n−1 layers divided as a function of the type element.

## Claims

### Claim 1

A method for generating an n dimensional vector as a shape descriptor of a model, comprising:
determining a type element of the vector to describe the basic shape of the model; and
calculating n−1 metric elements of the vector, each of which represents the percentage of all of a feature of the model falling into one of n−1 layers divided as a function of the type element.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the model is a 3D model.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the feature comprises a vertex, a triangle, or an edge of the 3D model.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the basic shape of the 3D model comprises cube, sphere and cylinder.

### Claim 5 (depends on 2)

The method according to claim 2, wherein the basic shape comprises plane, open cylinder, cylinder, ellipse and sphere.

### Claim 6 (depends on 4)

The method according to claim 4, wherein the type element of is calculated as a function of the three eigenvalues of the covariance matrix of the 3D model.

### Claim 7 (depends on 1, 2, 3, 4, 5, 6)

The method according to any one of claims 1-6, wherein the type element is an integer.

### Claim 8 (depends on 3)

The method according to claim 3, wherein the bounding box of the 3D model is divided by n−1 embedded shape determined according to the type element.

### Claim 9 (depends on 1)

The method according to claim 1, wherein the metric elements are all floats.

### Claim 10 (depends on 8)

The method according to claim 8, wherein one of the metric elements is calculated by the normalization of the percentage of all of a feature of the 3D model falling into one of n−1 layers.

### Claim 11

Apparatus for generating an n dimensional vector as a shape descriptor of a model, comprising:
means for determining a type element of the vector to describe the basic shape of the model; and
means for calculating n−1 metric elements of the vector, each of which represents the percentage of all of a feature of the model falling into one of n−1 layers divided as a function of the type element.

### Claim 12

A shape descriptor of a model, which is an n dimensional vector, comprising:
a type element for describing the basic shape of the model; and
n−1 metric elements of the vector, each of which represents the percentage of all of a feature of the model falling into one of n−1 layers divided as a function of the type element.
