# US 2023/0054098 A1 · Personal authentication apparatus and control method

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

- Number: US 2023/0054098 A1
- Document ID: US20230054098A1
- Status: Published application
- Kind: A1
- Application number: 17/873,309
- Filed: 2022-07-26
- Published: 2023-02-23
- Earliest claimed: 2021-08-17
- Assignees: Canon Kabushiki Kaisha
- Applicants: Canon Kabushiki Kaisha
- Inventors: Kazuhiro Namiki
- Web page: https://patentgrep.com/patent/US20230054098A1

## CPC

- G06V 40/193: {Preprocessing; Feature extraction}
- G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V 10/267: {by performing operations on regions, e.g. growing, shrinking or watersheds}
- G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]}
- G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 10/82: using neural networks
- G06V 40/197: {Matching; Classification}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A personal authentication apparatus comprises a first image capture unit that captures an eyeball image, a first image processing unit that obtains brightness information of the captured eyeball image and generates divided eyeball images by dividing a region of the eyeball image based on the brightness information of the eyeball image, a first storage unit that stores brightness information of the divided eyeball images and position information of the divided eyeball images in relation to the eyeball image in association with each other, and a learning unit that executes different types of learning processing respectively for the divided eyeball images in accordance with the brightness information and the position information of the divided eyeball images.

## Claims

### Claim 1

A personal authentication apparatus, comprising:
a memory and at least one processor and/or at least one circuit which function as:
a first image capture unit configured to capture an eyeball image;
a first image processing unit configured to obtain brightness information of the eyeball image captured by the first image capture unit, and generate divided eyeball images by dividing a region of the eyeball image based on the brightness information of the eyeball image;
a first storage unit configured to store brightness information of the divided eyeball images and position information of the divided eyeball images in relation to the eyeball image in association with each other; and
a learning unit configured to execute different types of learning processing respectively for the divided eyeball images in accordance with the brightness information and the position information of the divided eyeball images.

### Claim 2 (depends on 1)

The apparatus according to claim 1, wherein the processor and/or the circuit function as the following units:
a second image capture unit configured to capture an eyeball image;
a second image processing unit configured to obtain brightness information of the eyeball image captured by the second image capture unit, and generate divided eyeball images by dividing a region of the eyeball image based on the brightness information of the eyeball image;
a second storage unit configured to store brightness information of the divided eyeball images and position information of the divided eyeball images in relation to the eyeball image in association with each other;
an inference unit configured to execute inference processing for each of divided eyeball images with respect to eyeball images of a person to be registered and a person to be authenticated, which have been captured by the second image capture unit, with use of weight information of a learning device obtained through learning processing that has been performed by the learning unit for each of the divided eyeball images, and compute characteristic amounts of the divided eyeball images;
an authentication unit configured to perform authentication processing for collating the characteristic amounts of the respective divided eyeball images of the person to be registered with the characteristic amounts of the respective divided eyeball images of the person to be authenticated, the characteristic amounts having been computed by the inference unit; and
a notification unit configured to give notice of a result of the authentication processing performed by the authentication unit.

### Claim 3 (depends on 1)

The apparatus according to claim 1, wherein
in a case where the eyeball image includes a predetermined region in which a pixel value exceeds a predetermined value, the learning unit executes the learning processing with respect to a region other than the predetermined region.

### Claim 4 (depends on 2)

The apparatus according to claim 2, wherein
the first image processing unit and the second image processing unit set regions into which the eyeball image is divided based on a distribution of luminance values detected from the eyeball image.

### Claim 5 (depends on 2)

The apparatus according to claim 2, wherein
the brightness information includes a direction and an intensity of incidence of external light on an eyeball, and
the learning unit computes weights that are used when the inference unit executes machine learning for each of the divided eyeball images.

### Claim 6 (depends on 2)

The apparatus according to claim 2, wherein
the authentication unit performs the authentication processing by determining whether the number of divided eyeball images with a matching degree equal to or higher than a predetermined value is equal to or larger than a predetermined number, or whether a total of areas of divided eyeball images with a matching degree equal to or higher than a predetermined value is equal to or larger than a predetermined value.

### Claim 7

A method of controlling a personal authentication apparatus, comprising:
capturing an eyeball image;
obtaining brightness information of the captured eyeball image, and generating divided eyeball images by dividing a region of the eyeball image based on the brightness information of the eyeball image;
storing brightness information of the divided eyeball images and position information of the divided eyeball images in relation to the eyeball image in association with each other; and
executing different types of learning processing respectively for the divided eyeball images in accordance with the brightness information and the position information of the divided eyeball images.

### Claim 8

A non-transitory computer-readable storage medium storing a program for causing a computer to function as each unit of a personal authentication apparatus comprising a first image capture unit configured to capture an eyeball image;
a first image processing unit configured to obtain brightness information of the eyeball image captured by the first image capture unit, and generate divided eyeball images by dividing a region of the eyeball image based on the brightness information of the eyeball image;
a first storage unit configured to store brightness information of the divided eyeball images and position information of the divided eyeball images in relation to the eyeball image in association with each other; and
a learning unit configured to execute different types of learning processing respectively for the divided eyeball images in accordance with the brightness information and the position information of the divided eyeball images.
