# US 2012/0257803 A1 · Image processing apparatus, image processing method, and non-transitory computer readable storage medium

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

- Number: US 2012/0257803 A1
- Document ID: US20120257803A1
- Status: Published application
- Kind: A1
- Application number: 13/406,835
- Filed: 2012-02-28
- Published: 2012-10-11
- Earliest claimed: 2011-04-06
- Assignees: Fujitsu Limited
- Inventors: Akihiro MINAGAWA; Yutaka KATSUYAMA; Nobuyuki HARA; Yoshinobu HOTTA; Wei FAN
- Web page: https://patentgrep.com/patent/US20120257803A1

## CPC

- G06V 40/107: {Static hand or arm}
- G06F 3/04883: for inputting data by handwriting, e.g. gesture or text
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An image processing apparatus includes a central-portion extracting unit, a classifying unit and a determining unit. The central-portion extracting unit extracts edges from an image area and extracts a plurality of central portions of areas each of which is sandwiched between the edges. The classifying unit groups the central portions by classifying adjacent central portions that have no edge therebetween into a single group. The determining unit determines an area of finger, the area of finger being surrounded by the central portions classified into a group by the classifying unit and peripheral edges of the central portion, the area of finger being an area where a ratio of a luminance gradient in a short side direction to a luminance gradient in a long side direction is within a predetermined threshold.

## Claims

### Claim 1

An image processing apparatus comprising:
a central-portion extracting unit that extracts edges from an image area and extracts a plurality of central portions of areas each of which is sandwiched between the edges;
a classifying unit that groups the central portions by classifying adjacent central portions that have no edge therebetween into a single group; and
a determining unit that determines an area of finger, the area of finger being surrounded by the central portions classified into a group by the classifying unit and peripheral edges of the central portion, the area of finger being an area where a ratio of a luminance gradient in a short side direction to a luminance gradient in a long side direction is within a predetermined threshold.

### Claim 2 (depends on 1)

The image processing apparatus according to claim 1, wherein
the determining unit determines the area of finger in a rectangular area, the rectangular area being calculated based on the central portions classified into a group by the classifying unit and a pseudo skeleton obtained from peripheral edges of the central portions and values of distances from an edge of each point of the pseudo skeleton.

### Claim 3 (depends on 1)

The image processing apparatus according to claim 1, wherein
the central-portion extracting unit extracts a central portion whose distance from the corresponding edge is less than a predetermined threshold out of the central portions of the areas each of which is sandwiched between the edges.

### Claim 4 (depends on 1)

The image processing apparatus according to claim 1, wherein
the central-portion extracting unit obtains luminance gradients in a longitudinal direction and in a lateral direction with respect to a central portion of an area sandwiched between the edges, and extracts the central portion whose luminance gradients in the longitudinal direction and in the lateral direction are less than a predetermined threshold.

### Claim 5

An image processing method executed by a computer, the method comprising:
extracting edges from an image area and extracting a plurality of central portions of areas each of which is sandwiched between the edges;
grouping the central portions by classifying adjacent central portions that have no edge therebetween into a single group; and
determining an area of finger, the area of finger being surrounded by the central portions classified into a group and peripheral edges of the central portion, the area of finger being an area where a ratio of a luminance gradient in a short side direction to a luminance gradient in a long side direction is within a predetermined threshold.

### Claim 6 (depends on 5)

The image processing method according to claim 5, wherein
the determining determines the area of finger in a rectangular area, the rectangular area being calculated based on the central portions classified into a group and a pseudo skeleton obtained from peripheral edges of the central portions and values of distances from an edge of each point of the pseudo skeleton.

### Claim 7 (depends on 5)

The image processing method according to claim 5, wherein
the extracting extracts a central portion whose distance from the corresponding edge is less than a predetermined threshold out of the central portions of the areas each of which is sandwiched between the edges.

### Claim 8 (depends on 5)

The image processing method according to claim 5, wherein
the extracting obtains luminance gradients in a longitudinal direction and in a lateral direction with respect to a central portion of an area sandwiched between the edges, and extracts the central portion whose luminance gradients in the longitudinal direction and in the lateral direction are less than a predetermined threshold.

### Claim 9

A non-transitory computer readable storage medium having stored therein an image processing program for causing a computer to execute a process comprising:
extracting edges from an image area and extracting a plurality of central portions of areas each of which is sandwiched between the edges;
grouping the central portions by classifying adjacent central portions that have no edge therebetween into a single group; and
determining an area of finger, the area of finger being surrounded by the central portions classified into a group and peripheral edges of the central portion, the area of finger being an area where a ratio of a luminance gradient in a short side direction to a luminance gradient in a long side direction is within a predetermined threshold.

### Claim 10 (depends on 9)

The non-transitory computer-readable storage medium according to claim 9, wherein
the determining determines the area of finger in a rectangular area, the rectangular area being calculated based on the central portions classified into a group and a pseudo skeleton obtained from peripheral edges of the central portions and values of distances from an edge of each point of the pseudo skeleton.

### Claim 11 (depends on 9)

The non-transitory computer-readable storage medium according to claim 9, wherein
the extracting extracts a central portion whose distance from the corresponding edge is less than a predetermined threshold out of the central portions of the areas each of which is sandwiched between the edges.

### Claim 12 (depends on 9)

The non-transitory computer-readable storage medium according to claim 9, wherein
the extracting obtains luminance gradients in a longitudinal direction and in a lateral direction with respect to a central portion of an area sandwiched between the edges, and extracts the central portion whose luminance gradients in the longitudinal direction and in the lateral direction are less than a predetermined threshold.

### Claim 13

An image processing apparatus comprising:
a processor; and
a memory, wherein the processor executes:
extracting edges from an image area and extracting a plurality of central portions of areas each of which is sandwiched between the edges;
grouping the central portions by classifying adjacent central portions that have no edge therebetween into a single group; and
determining an area of finger, the area of finger being surrounded by the central portions classified into a group and peripheral edges of the central portion, the area of finger being an area where a ratio of a luminance gradient in a short side direction to a luminance gradient in a long side direction is within a predetermined threshold.
