# US 2020/0404120 A1 · Image processing apparatus

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

- Number: US 2020/0404120 A1
- Document ID: US20200404120A1
- Status: Published application
- Kind: A1
- Application number: 17/011,803
- Filed: 2020-09-03
- Published: 2020-12-24
- Earliest claimed: 2017-08-01
- Assignees: Kabushiki Kaisha Toshiba; Toshiba Tec Kabushiki Kaisha
- Applicants: Kabushiki Kaisha Toshiba; Toshiba Tec Kabushiki Kaisha
- Inventors: Hiromasa TANAKA
- Web page: https://patentgrep.com/patent/US20200404120A1

## CPC

- H04N 1/3872: {Repositioning or masking}
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 7/12: Edge-based segmentation
- G06T 2207/10008: from scanner, fax or copier
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/20132: Image cropping
- G06T 2207/30176: Document
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An image processing apparatus includes an interface through which scanned image data obtained by scanning a designated region, is acquired, and a processor. The processor extracts a contour line representing a document area from the scanned image data, extracts vertices of the contour line, determines whether a plurality of original documents is present in the document area based on the vertices, extracts document image data of each original document from the scanned image data, and generates one file including the extracted document image data for each original document.

## Claims

### Claim 1

An image processing apparatus, comprising:
a processor configured to:
extract a first outermost contour line of a first document area in image data of a plurality of documents,
extract a second outermost contour line of a second document area in the image data, the first document area and the second document area not overlapping with each other in the image data,
extract vertices of the first outermost contour line,
extract document image data of a first document and a second document in the first document area based on the extracted vertices of the first outermost contour line,
generate a first single file including the extracted document image data for the first document and the second document,
extract vertices of the second outermost contour line,
extract document image data of a third document and a fourth document in the second document area based on the extracted vertices of the second outermost contour line, and
generate a second single file including the extracted document image data for the third document and the fourth document; and
a memory configured to store the first single file and the second single file.

### Claim 2 (depends on 1)

The image processing apparatus according to claim 1, wherein
the first document and the second document partially overlap in the first document area, and
the third document and the fourth document partially overlap in the second document area.

### Claim 3 (depends on 1)

The image processing apparatus according to claim 1, wherein the image data is loaded from the memory.

### Claim 4 (depends on 1)

The image processing apparatus according to claim 1, wherein the processor is further configured to correct an inclination of the extracted document image data.

### Claim 5 (depends on 1)

The image processing apparatus according to claim 1, wherein the processor is configured to:
extract first to third vertices of the first outermost contour line that are adjacent to one another and form a right angle or an approximate right angle,
estimate a fourth vertex from the first to third vertices such that the first to fourth vertices form a rectangle or an approximate rectangle, and
extract document image data from the image data based on the rectangle or the approximate rectangle.

### Claim 6 (depends on 5)

The image processing apparatus according to claim 5, wherein the processor is configured to determine whether the rectangle is formed within the document area and extract the document image data from the image data only if the rectangle is inside the document area.

### Claim 7 (depends on 1)

The image processing apparatus according to claim 1, wherein the processor is configured to:
acquire the image data from the memory; and
perform a binarization process on the image data before extracting the first outermost contour line.

### Claim 8 (depends on 1)

The image processing apparatus according to claim 1, wherein the processor is further configured to calculate an overlap ratio for the first and second documents.

### Claim 9

A method of processing image data including a plurality of documents, the method comprising:
extracting a first outermost contour line of a first document area in image data of a plurality of documents;
extracting a second outermost contour line of a second document area in the image data, the first document area and the second document area not overlapping with each other in the image data;
extracting vertices of the first outermost contour line;
extracting document image data of a first document and a second document in the first document area based on the extracted vertices of the first outermost contour line;
generating a first single file including the extracted document image data for the first document and the second document;
extracting vertices of the second outermost contour line;
extracting document image data of a third document and a fourth document in the second document area based on the extracted vertices of the second outermost contour line;
generating a second single file including the extracted document image data for the third document and the fourth document; and
storing the first single file and the second single file in a memory.

### Claim 10 (depends on 9)

The method according to claim 9, wherein
the first document and the second document partially overlap in the first document area, and
the third document and the fourth document partially overlap in the second document area.

### Claim 11 (depends on 9)

The method according to claim 9, further comprising:
loading the image data from the memory.

### Claim 12 (depends on 9)

The method according to claim 9, further comprising:
correcting an inclination of the extracted document image data.

### Claim 13 (depends on 9)

The method according to claim 9, further comprising:
extracting first to third vertices of the first outermost contour line that are adjacent to one another and form a right angle or an approximate right angle;
estimating a fourth vertex from the first to third vertices such that the first to fourth vertices form a rectangle or an approximate rectangle; and
extracting document image data from the image data based on the rectangle or the approximate rectangle.

### Claim 14 (depends on 13)

The method according to claim 13, further comprising:
determining whether the rectangle is formed within the document area and extracting the document image data from the image data only if the rectangle is inside the document area.

### Claim 15 (depends on 9)

The method according to claim 9, further comprising:
acquiring the image data from the memory; and
performing a binarization process on the image data before extracting the first outermost contour line.

### Claim 16 (depends on 9)

The method according to claim 9, further comprising:
calculating an overlap ratio for the first and second documents.

### Claim 17

A non-transitory computer readable medium comprising instructions that are executable in an image processing apparatus, wherein the instructions when executed in the image processing apparatus cause the image processing apparatus to carry out a method of processing image data, said method comprising:
extracting a first outermost contour line of a first document area in image data of a plurality of documents;
extracting a second outermost contour line of a second document area in the image data, the first document area and the second document area not overlapping with each other in the image data;
extracting vertices of the first outermost contour line;
extracting document image data of a first document and a second document in the first document area based on the extracted vertices of the first outermost contour line;
generating a first single file including the extracted document image data for the first document and the second document;
extracting vertices of the second outermost contour line;
extracting document image data of a third document and a fourth document in the second document area based on the extracted vertices of the second outermost contour line;
generating a second single file including the extracted document image data for the third document and the fourth document; and
storing the first single file and the second single file in a memory.

### Claim 18 (depends on 17)

The non-transitory computer readable medium according to claim 17, wherein
the first document and the second document partially overlap in the first document area, and
the third document and the fourth document partially overlap in the second document area.

### Claim 19 (depends on 18)

The non-transitory computer readable medium according to claim 18, wherein the method further comprises:
calculating an overlap ratio for the first and second documents.

### Claim 20 (depends on 17)

The non-transitory computer readable medium according to claim 17, wherein the method further comprises:
acquiring the image data from the memory; and
performing a binarization process on the image data before extracting the first outermost contour line.
