# US 2019/0378290 A1 · Information processing apparatus and non-transitory computer readable medium storing information processing program

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

- Number: US 2019/0378290 A1
- Document ID: US20190378290A1
- Status: Published application
- Kind: A1
- Application number: 16/161,067
- Filed: 2018-10-16
- Published: 2019-12-12
- Earliest claimed: 2018-06-07
- Assignees: Fuji Xerox Co., Ltd.
- Applicants: Fuji Xerox Co., Ltd.
- Inventors: Yusuke YAMAURA; Yukihiro TSUBOSHITA; Takeshi ONISHI
- Web page: https://patentgrep.com/patent/US20190378290A1

## CPC

- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/242: {by image rotation, e.g. by 90 degrees}
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06V 40/168: {Feature extraction; Face representation}
- G06T 2207/20081: Training; Learning
- G06T 2207/30201: Face
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An information processing apparatus includes a receiving unit that receives a first image which has been extracted from an image obtained by imaging of an omnidirectional camera, the first image having been obtained by imaging a head of a person and position information indicating a position of the person in the image, a calculation unit that calculates a degree of distortion of the first image from the position information, and a learning unit that performs learning for estimating an orientation of a face of the person by using the calculated degree of distortion and the first image.

## Claims

### Claim 1

An information processing apparatus comprising:
a receiving unit that receives a first image which has been extracted from an image obtained by imaging of an omnidirectional camera, the first image having been obtained by imaging a head of a person and position information indicating a position of the person in the image;
a calculation unit that calculates a degree of distortion of the first image from the position information; and
a learning unit that performs learning for estimating an orientation of a face of the person by using the calculated degree of distortion and the first image.

### Claim 2 (depends on 1)

The information processing apparatus according to claim 1,
wherein an coordinate position of the person which is defined based on a specific point in the image, a distance from a specific point to the person, or a combination thereof is used as the position information.

### Claim 3 (depends on 2)

The information processing apparatus according to claim 2,
wherein a size of the person, a ratio between a horizontal length and a vertical length of a rectangle surrounding the person, or a combination thereof is further used as the position information.

### Claim 4 (depends on 3)

The information processing apparatus according to claim 3,
wherein the receiving unit further receives third position information indicating a position of an object other than the person, in the image, and
the learning unit performs the learning by further using the third position information.

### Claim 5 (depends on 4)

The information processing apparatus according to claim 4,
wherein the object other than the person is a product shelf, a product, a poster, a mannequin, a person other than the person, or a combination thereof.

### Claim 6

A non-transitory computer readable medium storing an information processing program causing a computer to function as:
a receiving unit that receives a first image which has been extracted from an image obtained by imaging of an omnidirectional camera, the first image having been obtained by imaging a head of a person and position information indicating a position of the person in the image;
a calculation unit that calculates a degree of distortion of the first image from the position information; and
a learning unit that performs learning for estimating an orientation of a face of the person by using the calculated degree of distortion and the first image.