# US 2008/0304751 A1 · Image processing apparatus, image forming apparatus, image processing system, and image processing method

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

- Number: US 2008/0304751 A1
- Document ID: US20080304751A1
- Status: Published application
- Kind: A1
- Application number: 12/133,989
- Filed: 2008-06-05
- Published: 2008-12-11
- Earliest claimed: 2007-06-06
- Assignees: Sharp Kabushiki Kaisha
- Inventors: Makoto Hayasaki
- Web page: https://patentgrep.com/patent/US20080304751A1

## CPC

- G06V 10/245: {by locating a pattern; Special marks for positioning}
- G06V 30/1475: {Inclination or skew detection or correction of characters or of image to be recognised}
- G06V 30/10: Character recognition
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

There are provided: a pattern detection process section for extracting a partial image made of pixels including a target pixel from input image data; a rotated image generating section for generating a self-rotated image by rotating the partial image; and a matching test determination section for determining whether an image pattern included in the partial image matches an image pattern included in the self-rotated image. When it is determined that matching exists, a target pixel in the partial image or a block made of pixels including the target pixel is regarded as a feature point. Consequently, even when image data has been read while skewed with respect to a predetermined positioning angle of a reading position of an image reading apparatus or image data has been subjected to enlarging, reducing etc., a feature point properly specifying the image data can be extracted regardless of skew, enlarging, reducing etc.

## Claims

### Claim 1

An image processing apparatus, comprising:
a feature point detection section for detecting feature points included in input image data; and
a features calculation section for calculating features of the input image data in accordance with relative positions of the feature points detected by the feature point detection section,
the feature point detection section including:
a partial image extraction section for extracting, from the input image data, a partial image made of a plurality of pixels including a target pixel;
a rotated image generating section for generating a self-rotated image by rotating the partial image by a predetermined angle;
a matching test determination section for determining whether an image pattern included in the partial image matches an image pattern included in the self-rotated image or not, when the partial image is caused to overlap the self-rotated image; and
a detection section for detecting, as each of the feature points, (a) a target pixel in the partial image including the image pattern determined by the matching test determination section as matching the image pattern included in the self-rotated image, or (b) a block made of a plurality of pixels including the target pixel.

### Claim 2 (depends on 1)

The image processing apparatus as set forth in claim 1, further comprising:
at least one of a storage section in which features of a reference image are stored and a reference image obtaining section for obtaining the features of the reference image from an external apparatus communicably connected with the image processing apparatus; and
a similarity calculation section for comparing the features of the input image data that are calculated by the features calculation section with the features of the reference image so as to calculate a similarity between the input image data and the reference image.

### Claim 3 (depends on 1)

The image processing apparatus as set forth in claim 1, further comprising:
a storage section in which features of image data and identification information for identifying image data are stored; and
a storage process section for causing the features of the input image data that are calculated by the features calculation section and identification information for identifying the input image data to be stored in the storage section in such a manner that the features are related to the identification information.

### Claim 4 (depends on 1)

The image processing apparatus as set forth in claim 1, further comprising a pattern detection process section for determining whether the partial image includes an image pattern or not,
the rotated image generating section generating the self-rotated image with respect to a partial image determined by the pattern detection process section as including an image pattern.

### Claim 5 (depends on 1)

The image processing apparatus as set forth in claim 1, wherein
the rotated image generating section generates a plurality of self-rotated images with respect to each partial image by rotating each partial image by different rotation angles,
the matching test determination section determines whether the partial image matches each of the plurality of self-rotated images, and
when the partial image matches at least one of the plurality of self-rotated images, the detection section detects, as each of the feature points, a target pixel in the partial image or a block made of a plurality of pixels including the target pixel.

### Claim 6 (depends on 1)

The image processing apparatus as set forth in claim 1, wherein the partial image extraction section extracts plural kinds of partial images by differentiating a size of an area to be extracted as a partial image.

### Claim 7 (depends on 6)

The image processing apparatus as set forth in claim 6, wherein
the partial image extraction section performs a first extraction process for extracting a partial image while setting a size of an area to be extracted as the partial image to be a first size, and a second extraction process for extracting a partial image while setting a size of an area to be extracted as the partial image to be a second size larger than the first size, and
in the second extraction process, the partial image is extracted after excluding the area with the first size from the area with the second size in such a manner that the area with the first size and the area with the second size center an identical target pixel.

### Claim 8 (depends on 1)

The image processing apparatus as set forth in claim 1, wherein the partial image extraction section extracts a partial image with respect to each of a plurality of color components of input image data.

### Claim 9 (depends on 1)

The image processing apparatus as set forth in claim 1, further comprising a smoothing process section for performing a smoothing process on input image data,
the feature point detection section detecting the feature points from the input image data subjected to the smoothing process.

### Claim 10 (depends on 1)

An image forming apparatus, comprising an image processing apparatus as set forth in claim 1 and an image output section for forming an image corresponding to input image data on a recording material.

### Claim 11

An image processing system, comprising an image processing apparatus and a server communicably connected with the image processing apparatus,
one of the image processing apparatus and the server including a feature point detection section for detecting feature points included in input image data and a features calculation section for calculating features of the input image data in accordance with relative positions of the feature points detected by the feature point detection section, or the feature point detection section and the features calculation section being divided into the image processing apparatus and the server,
the feature point detection section including:
a partial image extraction section for extracting, from the input image data, a partial image made of a plurality of pixels including a target pixel;
a rotated image generating section for generating a self-rotated image by rotating the partial image by a predetermined angle;
a matching test determination section for determining whether an image pattern included in the partial image matches an image pattern included in the self-rotated image or not, when the partial image is caused to overlap the self-rotated image; and
a detection section for detecting, as each of the feature points, (a) a target pixel in the partial image including the image pattern determined by the matching test determination section as matching the image pattern included in the self-rotated image, or (b) a block made of a plurality of pixels including the target pixel.

### Claim 12

An image processing method, comprising the steps of:
(I) detecting feature points included in input image data; and
(II) calculating features of the input image data in accordance with relative positions of the feature points detected in the step (I),
the step (I) including the substeps of:
(i) extracting, from the input image data, a partial image made of a plurality of pixels including a target pixel;
(ii) generating a self-rotated image by rotating the partial image by a predetermined angle;
(iii) determining whether an image pattern included in the partial image matches an image pattern included in the self-rotated image or not, when the partial image is caused to overlap the self-rotated image; and
(iv) detecting, as each of the feature points, (a) a target pixel in the partial image including the image pattern determined in the substep (iii) as matching the image pattern included in the self-rotated image, or (b) a block made of a plurality of pixels including the target pixel.

### Claim 13

A computer-readable storage medium in which a program for causing an image processing apparatus to operate is stored,
the image processing apparatus including:
a feature point detection section for detecting feature points included in input image data; and
a features calculation section for calculating features of the input image data in accordance with relative positions of the feature points detected by the feature point detection section,
the feature point detection section including:
a partial image extraction section for extracting, from the input image data, a partial image made of a plurality of pixels including a target pixel;
a rotated image generating section for generating a self-rotated image by rotating the partial image by a predetermined angle;
a matching test determination section for determining whether an image pattern included in the partial image matches an image pattern included in the self-rotated image or not, when the partial image is caused to overlap the self-rotated image; and
a detection section for detecting, as each of the feature points, (a) a target pixel in the partial image including the image pattern determined by the matching test determination section as matching the image pattern included in the self-rotated image, or (b) a block made of a plurality of pixels including the target pixel,
the program causing a computer to function as the feature point detection section.
