# US 6,731,789 B1 · Image processing apparatus and method, and storage medium

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

- Number: US 6,731,789 B1
- Document ID: US6731789B1
- Status: Granted
- Kind: B1
- Application number: 09/493,262
- Filed: 2000-01-28
- Granted: 2004-05-04
- Earliest claimed: 1999-01-29
- Assignees: Canon Kabushiki Kaisha
- Inventors: Hiroshi Tojo
- Web page: https://patentgrep.com/patent/US6731789B1

## CPC

- G06F 16/5838: {using colour}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

This invention converts given color label string data into another color label string data without requiring any original image. For this purpose, a color label string input unit (2010) inputs a color label string pertaining to a source image and its attribute information. A conversion attribute destination unit (2020) designates attribute information that pertains to labeling of a destination color space. A color space matching unit (2030) attains color space matching for the input color label string on the basis of the input attribute information and designated attribute information. A block segmentation matching unit (2040) attains matching with destination blocks, and a color label string output unit (2050) generates and outputs a destination color label string.

## Claims

### Claim 1

An image processing apparatus which segments an image into a plurality of blocks, and expresses the image by color label string data by assigning color labels to the segmented blocks in correspondence with feature amounts, comprising:
input means for inputting source color label string data and attribute information thereof;
designation means for designating attribute information of converted color label string data;
determination means for determining whether or not the attribute information of the source color label string data is the same as the attribute information of the converted color label string data designated by said designation means; and
conversion means for, if said determination means determines that the attribute information of the source color label string data is not the same as the attribute information of the converted color label string data, converting the source color label string data into destination color label string data on the basis of the attribute information input by said input means, and the attribute information designated by said designation means.

### Claim 2 (depends on 1)

The apparatus according to claim 1, wherein the attribute information includes a type of color space, the number of labels corresponding to the number of small color space segments that form a color space, and the number of segmented blocks of an image.

### Claim 3 (depends on 1)

The apparatus according to claim 1, wherein said conversion means comprises:
means for obtaining an intermediate color of each color label in a source color space; and
means for obtaining a destination color label by mapping the obtained intermediate color into a destination color space.

### Claim 4 (depends on 1)

The apparatus according to claim 1, wherein when a first block size defined by the number of segmented blocks of the source image is a fraction of a second block size defined by the number of segmented blocks of the destination image, a histogram of labels of blocks having the first block size included in a block having the second block size is computed, a label with the highest frequency of occurrence is determined to be a representative label, and a destination label is assigned based on the representative label.

### Claim 5 (depends on 4)

The apparatus according to claim 4, wherein the representative label is determined under a condition that identical labels are in the majority of the number of blocks having the first block size included in the block having the second block size.

### Claim 6 (depends on 4)

The apparatus according to claim 4, wherein when the label having the highest frequency of occurrence cannot be specified, color labels assigned at approximate positions in terms of a color space are determined to be identical labels.

### Claim 7 (depends on 4)

The apparatus according to claim 4, wherein the representative label for assigning to the destination label is computed by weighting as color labels with the frequencies of occurrence of the color labels.

### Claim 8 (depends on 6)

The apparatus according to claim 6, wherein the approximate positions in terms of the color space have a shortest distance in the color space.

### Claim 9 (depends on 6)

The apparatus according to claim 6, wherein when the color labels which are determined to be identical color labels are not in the majority, a representative label is determined by labels assigned to blocks within a predetermined range larger than the block of interest having the second block size.

### Claim 10 (depends on 9)

The apparatus according to claim 9, wherein when the representative label cannot be determined by the labels assigned to blocks within a predetermined range larger than the block having the second block size, a label of a block located at a predetermined position is determined to be the representative block.

### Claim 11 (depends on 1)

The apparatus according to claim 1, wherein said conversion means comprises computing means for computing color information in a destination color space on the basis of color information expressed by labels of a source color space, when a type of source color space is different from a type of destination color space.

### Claim 12

An image processing method which segments an image into a plurality of blocks, and expresses the image by color label string data by assigning color labels to the segmented blocks in correspondence with feature amounts, comprising:
an input step, of inputting source color label string data and attribute information thereof;
a designation step, of designating attribute information of converted color label string data;
a determination step, of determining whether or not the attribute information of the source color label string data is the same as the attribute information of the converted color label string data designated in said designation step; and
a conversion step, of, if it is determined in said determination step that the attribute information of the source color label string data is not the same as the attribute information of the converted color label string data, converting the source color label string data into destination color label string data on the basis of the attribute information input in said input step, and the attribute information designated in said designation step.

### Claim 13

A storage medium, capable of being read by a computer, storing a program for executing a method for controlling an image processing apparatus, which segments an image into a plurality of blocks, and expresses the image by color label string data by assigning color labels to the segmented blocks in correspondence with feature amounts, when the program code is loaded and executed by a computer, the method comprising the steps of:
inputting source color label string data and attribute information thereof;
designating attribute information of converted color label string data;
determining whether or not the attribute information of the source color label string data is the same as the attribute information of the converted color label data designated in said designation step; and
if it is determined in said determination step that the attribute information of the source color label string data is not the same as the attribute information of the converted color label string data, converting the source color label string data into destination color label string data on the basis of the attribute information input in said input step, and the attribute information designated in said designation step.

### Claim 14

A computer program product stored in a computer readable medium for executing an image processing method which segments an image into a plurality of blocks, and expresses the image by color label string data by assigning color labels to the segmented blocks in correspondence with feature amounts, said program comprising:
code for an input step, of inputting source color label string data and attribute information thereof;
code for a designation step, of designating attribute information of converted color label string data;
code for a determination step, of determining whether or not the attribute information of the source color label string data is the same as the attribute information of the converted color label string data designated in said designation step; and
code for a conversion step, of if it is determined in said determination step that the attribute information of the source color label string data is not the same as the attribute information of the converted color label string data, converting the source color label string data into destination color label string data on the basis of the attribute information input in said input step, and the attribute information designated in said designation step.
