# US 2023/0419738 A1 · Video processing apparatus, method for controlling the same, and non-transitory computer-readable storage medium

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

- Number: US 2023/0419738 A1
- Document ID: US20230419738A1
- Status: Published application
- Kind: A1
- Application number: 18/318,070
- Filed: 2023-05-16
- Published: 2023-12-28
- Earliest claimed: 2022-06-28
- Assignees: Canon Kabushiki Kaisha
- Applicants: Canon Kabushiki Kaisha
- Inventors: Kimimaru KATO
- Web page: https://patentgrep.com/patent/US20230419738A1

## CPC

- G06V 10/56: relating to colour
- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- G06V 40/162: {using pixel segmentation or colour matching}
- G06V 40/168: {Feature extraction; Face representation}
- G06V 40/172: {Classification, e.g. identification}
- G06V 40/45: {Detection of the body part being alive}
- H04N 1/60: Colour correction or control {(H04N1/54 takes precedence)}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

The present invention provides a technique for determining whether an object is a living body with a high degree of accuracy even for a relatively short video of about one second. To achieve this, a video processing apparatus configured to determine whether an object is a living body from video data of the object constituted by a plurality of frames, comprises a correction unit configured to correct each of the plurality of frames constituting the video data based on a correction coefficient for correcting to colors of a plurality of target hues different from each other; and a determination unit configured to determine whether the object is a living body based on an average hue value of a skin area of the object in each of the plurality of frames being corrected.

## Claims

### Claim 1

A video processing apparatus configured to determine whether an object is a living body from video data of the object constituted by a plurality of frames, comprising:
a processor; and
a memory storing instructions which, when read and executed by the processor, cause the apparatus to function as:
a correction unit configured to correct each of the plurality of frames constituting the video data based on a correction coefficient for correcting to colors of a plurality of target hues different from each other; and
a determination unit configured to determine whether the object is a living body based on an average hue value of a skin area of the object in each of the plurality of frames being corrected.

### Claim 2 (depends on 1)

The apparatus according to claim 1, further comprising a decision unit configured to decide the correction coefficient for approximating a color of the skin area in each of the plurality of frames constituting the video data to a predetermined target hue.

### Claim 3 (depends on 2)

The apparatus according to claim 2, wherein
when the number of the plurality of target hues is n, and an i-th (1≤i≤n) target hue among the plurality of target hues is defined as tagH(i),
the decision unit
decides a color represented by average values aveR, aveG, and aveB of values of respective color components of all pixels in a skin area of a predetermined representative frame in the video data as a color of the skin area, and
decides Ar, Ag, and Ab that are ratios between the color component values aveR, aveG, and aveB representing the color of the skin area and the color component values tagR, tagG, and tagB representing the color of the target hue tagH(i) as the correction coefficients of the target hue tagH(i), and
the correction unit generates a frame for the target hue tagH(i) by multiplying a value of each color component of RGB of pixels in the skin area of the plurality of frames by the correction coefficients Ar, Ag, and Ab of the respective components being decided.

### Claim 4 (depends on 1)

The apparatus according to claim 1, wherein the plurality of target hues are values representing directions represented by predetermined angle increments when a direction of an R component is 0°, a direction of a G component is 120°, and a direction of a B component is 240°.

### Claim 5 (depends on 1)

The apparatus according to claim 1, wherein
when the number of the plurality of target hues is n, and an i-th (1≤i≤N) target hue among the plurality of target hues is defined as tagH(i),
the determination unit acquires determination result of a living body by
performing processing to obtain, as an amplitude value amp(H(i)) of the target hue tagH(i), a difference between a maximum value and a minimum value of the hue of the skin area of the video data of the target hue tagH(i) generated by the correction unit,
obtaining a total sum of an amplitude values amp(H(1)) to amp(H(N)),
obtaining amp_r(H(1)) to amp_r(H(N)) representing ratios by dividing each of the amplitude values amp(H(1)) to amp(H(N)) by the total sum, and
supplying the amp_r(H(1)) to amp_r(H(N)) to a discriminator that determines whether a living body is a living body learned in advance.

### Claim 6 (depends on 1)

The apparatus according to claim 1, further comprising an extraction unit configured to extract a skin area of the object from each of the plurality of frames constituting the video data, wherein
the correction unit corrects, based on the correction coefficient, the skin area being extracted.

### Claim 7 (depends on 1)

The apparatus according to claim 1, wherein the extraction unit acquires the skin area corresponding to the face of the object from the video data.

### Claim 8 (depends on 5)

The apparatus according to claim 5, further comprising
an acquisition unit configured to acquire information representing an imaging condition when the video data is imaged;
a plurality of discriminators corresponding to imaging conditions different from each other; and
a selection unit configured to select one of the plurality of discriminators based on the information acquired by the acquisition unit, wherein
the determination unit performs living body determination using the discriminator selected by the selection unit.

### Claim 9 (depends on 8)

The apparatus according to claim 8, wherein the imaging condition includes a color temperature and illuminance of illumination used when the video data is acquired.

### Claim 10

A method of controlling a video processing apparatus configured to determine whether an object is a living body from video data of the object constituted by a plurality of frames, the method comprising:
correcting each of the plurality of frames constituting the video data based on a correction coefficient for correcting to colors of a plurality of target hues different from each other; and
determining whether the object is a living body based on an average hue value of a skin area of the object in each of the plurality of frames being corrected.

### Claim 11

A non-transitory computer-readable storage medium storing a program which, when read and executed by a computer, causes the computer to perform the step of a method of controlling a video processing apparatus configured to determine whether an object is a living body from video data of the object constituted by a plurality of frames, the method comprising:
correcting each of the plurality of frames constituting the video data based on a correction coefficient for correcting to colors of a plurality of target hues different from each other; and
determining whether the object is a living body based on an average hue value of a skin area of the object in each of the plurality of frames being corrected.
