# US 2012/0250987 A1 · System and method for effectively performing an image identification procedure

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

- Number: US 2012/0250987 A1
- Document ID: US20120250987A1
- Status: Published application
- Kind: A1
- Application number: 13/065,874
- Filed: 2011-03-31
- Published: 2012-10-04
- Earliest claimed: 2011-03-31
- Assignees: Sony Corporation
- Inventors: Liangyin Yu; Ming-Chang Liu
- Web page: https://patentgrep.com/patent/US20120250987A1

## CPC

- G06V 10/242: {by image rotation, e.g. by 90 degrees}
- G06V 10/20: Image preprocessing
- G06V 10/24: Aligning, centring, orientation detection or correction of the image
- G06V 10/243: {by compensating for image skew or non-uniform image deformations}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A system and method for effectively performing an image identification procedure includes an image matching manager that derives source characteristics for a source image and target characteristics for target images. The image matching manager compares the source characteristics and the target characteristics to determine whether the source image matches any of the target images. The source characteristics and the target characteristics may include color-space characteristics and curve-space characteristics from the respective images. A processor of an electronic device typically controls the image matching manager to effectively perform the image identification procedure.

## Claims

### Claim 1

A system for performing an image identification procedure, comprising:
an image manager that derives source characteristics for a source image and target characteristics for at least one target image, said image manager comparing said source characteristics and said target characteristics to determine whether said source image and said target image are matched, said source characteristics and said target characteristics each including color-space characteristics and curve-space characteristics; and
a processor of an electronic device that controls said image manager to perform said image identification procedure.

### Claim 2 (depends on 1)

The system of claim 1 wherein said image manager compares said source characteristics to a database of said target characteristics to identify one or more matching target images.

### Claim 3 (depends on 2)

The system of claim 2 wherein said source image has been subjected to an image modification procedure to produce said one or more matching images, said image modification procedure alternately including any of a scaling operation, a color modification, a cropping operation, a rotation operation, and a translation operation.

### Claim 4 (depends on 1)

The system of claim 1 wherein said image manager performs a down-sampling procedure on said source image during said image identification procedure.

### Claim 5 (depends on 1)

The system of claim 1 wherein said image manager performs a spectral filtering procedure on said source image during said image identification procedure.

### Claim 6 (depends on 2)

The system of claim 2 wherein said image manager performs a segmentation procedure on said source image during said image identification procedure.

### Claim 7 (depends on 6)

The system of claim 6 wherein said segmentation procedure divides said source image into dominant regions that are defined by segmentation criteria that include a region size and a region color.

### Claim 8 (depends on 7)

The system of claim 7 wherein said dominant regions define at least one characteristic curve as a boundary between said dominant regions.

### Claim 9 (depends on 8)

The system of claim 8 wherein said image manager calculates a color difference value for said source image, said color difference value being based upon color characteristics from said dominant regions on either side of said characteristic curve.

### Claim 10 (depends on 9)

The system of claim 9 wherein said color characteristics are derived from pixels located in two pixel bands that are immediately adjacent to said characteristic curve.

### Claim 11 (depends on 9)

The system of claim 9 wherein said color-space matching procedure is performed by utilizing CIED 2000 calculation techniques.

### Claim 12 (depends on 9)

The system of claim 9 wherein said image manager performs a color-space matching procedure by comparing respective color difference values for said source image and said target image.

### Claim 13 (depends on 12)

The system of claim 12 wherein said image manager performs a curve-space matching procedure by calculating a curvature distance value between characteristic curves of said source image and said target image.

### Claim 14 (depends on 13)

The system of claim 13 wherein said image manager performs a curve re-sampling procedure during said curve-space matching procedure.

### Claim 15 (depends on 13)

The system of claim 13 wherein said image manager computes a cumulated curvature distance as a cost function during said curve-space matching procedure.

### Claim 16 (depends on 13)

The system of claim 13 wherein said image manager utilizes level set techniques to solve a cost-minimization equation for deriving a minimum cost as a measure of curve differences during said curve-space matching procedure.

### Claim 17 (depends on 16)

The system of claim 16 wherein said image manager compares said minimum cost to a pre-defined threshold value to determine whether said characteristic curves match.

### Claim 18 (depends on 1)

The system of claim 1 wherein said image identification procedure is utilized to determine whether said target image is an illegal usage of copyrighted image material.

### Claim 19 (depends on 1)

The system of claim 1 wherein said image identification procedure is utilized to determine whether said target image is a modified form of said source image.

### Claim 20

A method for performing an image identification procedure, comprising the steps of:
utilizing an image manager to derive source characteristics for a source image and target characteristics for at least one target image, said image manager comparing said source characteristics and said target characteristics to determine whether said source image and said target image are matched, said source characteristics and said target characteristics each including color-space characteristics and curve-space characteristics; and
controlling said image manager with a processor of an electronic device to perform said image identification procedure.
