# US 2006/0039608 A1 · Background area extraction in document layout analysis

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

- Number: US 2006/0039608 A1
- Document ID: US20060039608A1
- Status: Published application
- Kind: A1
- Application number: 11/201,366
- Filed: 2005-08-11
- Published: 2006-02-23
- Earliest claimed: 2004-08-18
- Assignees: Ricoh Company, Ltd.
- Inventors: Hirobumi Nishida
- Web page: https://patentgrep.com/patent/US20060039608A1

## CPC

- G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An apparatus, method, system, computer program and product, each capable of extracting a background area of a document image. The background area of the document image may be extracted by repeating recursively the acts of: extracting a set of white rectangles from a processed area of the document image; dividing the processed area into a plurality of segments using the set of white rectangles as a separator; storing the plurality of segments; and reading the plurality of segments in a predetermined order as a processed area.

## Claims

### Claim 1

An apparatus for extracting a background area of a document image, comprising:
means for extracting a set of white rectangles from a processed area of the document image;
means for dividing the processed area into a plurality of segments using the set of white rectangles as a separator;
means for storing the plurality of segments; and
means for reading the plurality of segments in a predetermined order as a processed area,
wherein the extracting means, the dividing means, the storing means, and reading means repeat recursively the functions of extracting, dividing, storing, and reading, until the background area of the document image is extracted.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the extracting means comprises:
means for extracting a plurality of white rectangles covering white pixels of the document image, including the set of white rectangles;
means for calculating an evaluation function value for each of the plurality of white rectangles;
means for obtaining a lower boundary value of the evaluation function; and
means for selecting one or more white rectangles from the plurality of white rectangles as the set of white rectangles based on the evaluation function values.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the selecting means comprises:
means for eliminating one or more white rectangles having the evaluation function values smaller than the lower boundary value.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the selecting means further comprises:
means for listing the plurality of white rectangles in an order determined by the evaluation function values.

### Claim 5 (depends on 1)

The apparatus of claim 1, further comprising:
means for extracting a plurality of black rectangles covering black pixels from the processed area of the document image,
wherein the set of white rectangles is extracted from an area excluding the plurality of black rectangles.

### Claim 6 (depends on 2)

The apparatus of claim 2, wherein the evaluation function value corresponds to an area of the white rectangle.

### Claim 7 (depends on 2)

The apparatus of claim 2, wherein the lower boundary value is defined based on a dimension of the processed area.

### Claim 8 (depends on 2)

The apparatus of claim 2, wherein the extracting means further comprises:
means for obtaining statistical information of the processed area.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein the lower boundary value is defined based on the statistical information.

### Claim 10 (depends on 8)

The apparatus of claim 8, wherein the selecting means comprises:
means for estimating an appropriate dimension of the white rectangle using the statistical information; and
means for eliminating one or more white rectangles having inappropriate dimensions different from the appropriate dimension.

### Claim 11 (depends on 1)

The apparatus of claim 1, further comprising:
means for outputting the document image divided into plurality of segments.

### Claim 12 (depends on 4)

The apparatus of claim 4, wherein the predetermined order of the reading means corresponds to the order of the listing means.

### Claim 13

A method of extracting a background area of a document image, comprising the steps of:
extracting a set of white rectangles from a processed area of the document image;
dividing the processed area into a plurality of segments using the set of white rectangles as a separator;
storing the plurality of segments;
reading the plurality of segments in a predetermined order as a processed area,
wherein the steps of extracting, dividing, storing, and reading are repeated recursively until the background area of the document image is extracted.

### Claim 14 (depends on 13)

The method of claim 13, wherein the extracting step further comprises the steps of:
extracting a plurality of white rectangles covering white pixels of the document image, including the set of white rectangles;
calculating an evaluation function value for each of the plurality of white rectangles;
obtaining a lower boundary value of the evaluation function; and
selecting one or more white rectangles from the plurality of white rectangles as the set of white rectangles based on the evaluation function values.

### Claim 15 (depends on 13)

The method of claim 13, further comprising the step of:
outputting the document image divided into the plurality of segments.

### Claim 16

An image processing system, comprising:
a processor; and
a storage device configured to store a plurality of instructions which, when activated by the processor, cause the processor to perform an image processing operation comprising the steps of:
inputting a document image including a background area;
extracting a set of white rectangles from a processed area of the document image;
dividing the processed area into a plurality of segments using the set of white rectangles as a separator;
storing the plurality of segments in a memory; and
reading the plurality of segments in a predetermined order from the memory as a processed area,
wherein the steps of extracting, dividing, storing, and reading are repeated recursively until the background area of the document image is extracted.

### Claim 17 (depends on 16)

The system of claim 16, wherein the predetermined order of the reading step corresponds to a data structure of the memory.

### Claim 18 (depends on 16)

The system of claim 16, wherein the image processing operation further comprises the step of:
outputting the document image divided into the plurality of segments.

### Claim 19

A computer readable medium storing computer instructions for performing an image processing operation comprising:
inputting a document image including a background area;
extracting a set of white rectangles from a processed area of the document image;
dividing the processed area into a plurality of segments using the set of white rectangles as a separator;
storing the plurality of segments; and
reading the plurality of segments in a predetermined order as a processed area,
wherein the steps of extracting, dividing, storing, and reading are repeated recursively until the background area of the document image is extracted.

### Claim 20 (depends on 19)

The medium of claim 19, wherein the image processing operation further comprises the step of:
outputting the document image divided into the plurality of segments.
