# US 2017/0286758 A1 · Image processing apparatus, image processing method, and storage medium that recognize an image based on a designated object type

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

- Number: US 2017/0286758 A1
- Document ID: US20170286758A1
- Status: Published application
- Kind: A1
- Application number: 15/631,728
- Filed: 2017-06-23
- Published: 2017-10-05
- Earliest claimed: 2014-05-21
- Assignees: Canon Kabushiki Kaisha
- Applicants: Canon Kabushiki Kaisha
- Inventors: Yuichi Tsunematsu
- Web page: https://patentgrep.com/patent/US20170286758A1

## CPC

- G06V 40/16: Human faces, e.g. facial parts, sketches or expressions
- G06T 7/60: Analysis of geometric attributes
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V 40/172: {Classification, e.g. identification}
- H04N 23/61: based on recognised objects
- H04N 23/661: Transmitting camera control signals through networks, e.g. control via the Internet
- H04N 23/80: Camera processing pipelines; Components thereof
- G06V 40/178: {estimating age from face image; using age information for improving recognition}
- G06V 40/179: {metadata assisted face recognition}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

An image processing apparatus including an acquisition unit configured to acquire results of analysis processing for a plurality of images; a designation unit configured to designate a type of a target to be detected from an image; and a determination unit configured to determine, among the plurality of images, an image used for detection processing of the detection target designated by the designation unit based on the type of the detection target designated by the designation unit and the result of the analysis processing.

## Claims

### Claim 1

An image processing apparatus comprising:
a hardware processor; and
a memory storing instructions executable by the hardware processor,
wherein the hardware processor executes the instructions stored in the memory to execute:
an acquisition task that acquires information from each of a plurality of images, wherein the information is related to a part of an object detected in each of the plurality of images;
a designation task that accepts designation of a type of a target object, wherein the type is related to the part of the object detected in the plurality of images;
a selection task that selects, from among the plurality of images, at least one image based on the type designated by the designation task,
a detection task that detects the target object with regard to the images selected by the selection task.

### Claim 2 (depends on 1)

The image processing apparatus according to claim 1, wherein:
the information indicates a direction of a face detected in the image; and
the selection task, when the designation includes at least one feature of a gender, an age, or a face as the type of the target object, selects at least one image based on the information of the direction of the face.

### Claim 3 (depends on 1)

The image processing apparatus according to claim 1, wherein:
the information indicates a part of a human body in the image; and
the selection task, when the designation includes at least one of a body height, clothes, or belongings as the type of the target object, selects at least one image based on the information of the part of the human body.

### Claim 4 (depends on 1)

The image processing apparatus according to claim 1, wherein:
the information indicates a size of a human body in the image; and
the selection task selects, an image corresponding to a larger size of the human body.

### Claim 5 (depends on 1)

The image processing apparatus according to claim 1, wherein the hardware processor executes the instructions stored in the memory to further execute:
a holding task that holds identification of an image applied to the detection of the target object for each type that is designatable by the designation task.

### Claim 6

An image processing method comprising the steps of:
acquiring information from each of a plurality of images, wherein the information is related to a part an object detected in each of the plurality of images;
accepting designation of a type of a target object, wherein the type is related to the part of an object detected in the plurality of images;
selecting, from among the plurality of images, at least one image based on the type designated in the accepting step; and
detecting the target object with regard to the images selected in the selecting step.

### Claim 7 (depends on 6)

The image processing method according to claim 6, wherein:
the information indicates a direction of a face detected in the image; and
the selection step, when the designation includes at least one feature of a gender, an age, or a face as the type of the target object, selects at least one image based on the information of the direction of the face.

### Claim 8 (depends on 6)

The image processing method according to claim 6, wherein:
the information indicates a part of a human body in the image; and
the selection step, when the designation includes at least one of a body height, clothes, or belongings as the type of the target object, selects at least one image based on the information of the part of the human body.

### Claim 9 (depends on 6)

The image processing method according to claim 6, wherein:
the information indicates a size of a human body in the image; and
the selection step selects, an image corresponding to a larger size of the human body.

### Claim 10

A non-transitory computer-readable medium storing a program executable by a computer to execute a method comprising the steps of:
acquiring information from each of a plurality of images, wherein the information is related to a part an object detected in each of the plurality of images;
accepting designation of a type of a target object, wherein the type is related to the part of an object detected in the plurality of images;
selecting, from among the plurality of images, at least one image based on the type designation; and
detecting the target object with regard to the images selected in the selection step.
