# US 2012/0250952 A1 · Adaptive face recognition using online learning

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

- Number: US 2012/0250952 A1
- Document ID: US20120250952A1
- Status: Published application
- Kind: A1
- Application number: 13/078,924
- Filed: 2011-04-01
- Published: 2012-10-04
- Earliest claimed: 2011-04-01
- Assignees: Intel Corporation
- Inventors: Branislav Kveton; Kenton M. Lyons
- Web page: https://patentgrep.com/patent/US20120250952A1

## CPC

- G06V 40/16: Human faces, e.g. facial parts, sketches or expressions
- G06V 40/50: Maintenance of biometric data or enrolment thereof
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

In one embodiment an electronic device comprises an input/output module, a memory coupled to the input/output module, and logic to store a first image of a face in the memory module, associate an identity with the first image of a face, subsequently collect a second image of a face, determine a correlation between features on the first image of a face and the second image of a face, and store the correlation between the first image and the second image. Other embodiments may be described.

## Claims

### Claim 1

A method, comprising:
storing a first image of a face in a memory;
associating an identity with the first image of a face;
subsequently collecting a second image of a face;
determining a correlation between features on the first image of a face and the second image of a face; and
storing the correlation between the first image and the second image.

### Claim 2 (depends on 1)

The method of claim 1, wherein associating an identity with at least a first image of the face comprises receiving an identifier associated with the face via an input/output module.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining a correlation between features on the first image of a face and the second image of a face comprises determining a distance parameter between the first image and the second image.

### Claim 4 (depends on 3)

The method of claim 3, wherein determining a correlation between features on the first image of a face and the second image of a face further comprises dividing the distance parameter by a heat parameter.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
establishing a logical association between the first image of a face and the second image of a face.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
collecting a plurality of additional images of faces;
storing the additional images in the memory; and
constructing a graph which provides a logical link between images of faces on the graph.

### Claim 7 (depends on 6)

The method of claim 6, wherein:
each image of a face is represented as a node on the graph; and
the graph comprises correlations between images.

### Claim 8

An electronic device, comprising:
an input/output module;
a memory coupled to the input/output module; and
logic to:
store a first image of a face in the memory;
associate an identity with the first image of a face;
subsequently collect a second image of a face;
determine a correlation between features on the first image of a face and the second image of a face; and
store the correlation between the first image and the second image.

### Claim 9 (depends on 8)

The electronic device of claim 8, further comprising logic to receive an identifier associated with the face via the input/output module.

### Claim 10 (depends on 8)

The electronic device of claim 8, further comprising logic to determine a distance parameter between the first image and the second image.

### Claim 11 (depends on 10)

The electronic device of claim 10, further comprising logic to divide the distance parameter by a heat parameter.

### Claim 12 (depends on 8)

The electronic device of claim 8, further comprising logic to:
establish a logical association between the first image of a face and the second image of a face.

### Claim 13 (depends on 12)

The electronic device of claim 12, further comprising logic to:
collecting a plurality of additional images of faces;
storing the images in the memory module; and
constructing a graph which provides a logical link between images of faces.

### Claim 14 (depends on 13)

The electronic device of claim 13, wherein:
each image of a face is represented as a node on the graph; and
the graph comprises correlations between images.

### Claim 15

A computer program product comprising logic instruction stored on a tangible computer-readable medium which, when executed by a processor, configure the processor to implement a method, comprising:
storing a first image of a face in a memory;
associating an identity with the first image of a face;
subsequently collecting a second image of a face;
determining a correlation between features on the first image of a face and the second image of a face; and
storing the correlation between the first image and the second image.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein associating an identity with at least a first image of the face comprises receiving an identifier associated with the face via an input/output module.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein determining a correlation between features on the first image of a face and the second image of a face comprises determining a distance parameter between the first image and the second image.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein determining a correlation between features on the first image of a face and the second image of a face further comprises dividing the distance parameter by a heat parameter.

### Claim 19 (depends on 15)

The computer program product of claim 15, further comprising:
establishing a logical association between the first image of a face and the second image of a face.

### Claim 20 (depends on 15)

The computer program product of claim 15, further comprising:
collecting a plurality of additional images of faces;
storing the additional images in the memory; and
constructing a graph which provides a logical link between images of faces.

### Claim 21 (depends on 20)

The computer program product of claim 20, wherein:
each image of a face is represented as a node on the graph;
images which have correlations that exceed the first threshold value are linked to one another on the graph; and
images which have correlations does not exceed second threshold value are isolated on the graph as outliers.
