# US 2026/0087788 A1 · Learning apparatus and non-transitory computer-readable medium

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

- Number: US 2026/0087788 A1
- Document ID: US20260087788A1
- Status: Published application
- Kind: A1
- Application number: 19/409,113
- Filed: 2025-12-04
- Published: 2026-03-26
- Earliest claimed: 2023-06-07
- Assignees: Nikon Corporation
- Applicants: Nikon Corporation
- Inventors: Yosuke Otsubo; Yuuya Takayama; Kohei Kadoi; Shunsuke Takei; Takeshi Hataguchi
- Web page: https://patentgrep.com/patent/US20260087788A1

## CPC

- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 10/40: Extraction of image or video features
- G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]}
- G06V 10/766: using regression, e.g. by projecting features on hyperplanes
- G06V 10/82: using neural networks
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/698: {Matching; Classification}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A learning apparatus includes: a storage unit which stores a learning model trained by setting, as an input, a training image set and a training feature value set related to a subject of the training image set and obtained by quantifying a predetermined interpretable feature, and by setting, as an output, results of a determination on the training image set and the training feature value set; a determination unit which outputs, by using the learning model stored in the storage unit, results of a determination on a target image and a first feature value related to a subject of the target image and obtained by quantifying the predetermined interpretable feature; and an explanation output unit which outputs degrees of contribution of the target image and the first feature value, for the result of the determination on the target image and the first feature value by the learning model.

## Claims

### Claim 1

A learning apparatus comprising:
a storage unit which stores a learning model that is trained by setting, as an input, a training image set and a training feature value set that is related to a subject of the training image set and that is obtained by quantifying a predetermined interpretable feature, and by setting, as an output, results of a determination on the training image set and the training feature value set;
a determination unit which outputs, by using the learning model stored in the storage unit, results of a determination on a target image and a first feature value that is related to a subject of the target image and that is obtained by quantifying the predetermined interpretable feature; and
an explanation output unit which outputs a degree of contribution of the target image and a degree of contribution of the first feature value, for the result of the determination on the target image and the first feature value by the learning model.

### Claim 2 (depends on 1)

The learning apparatus according to claim 1, wherein the predetermined interpretable feature includes a parameter for quantitatively representing a shape or a characteristic of the subject.

### Claim 3 (depends on 1)

The learning apparatus according to claim 1, wherein
the determination unit extracts a second feature value from the target image, by using the learning model, and
the explanation output unit calculates each degree of contribution, by performing linear regression on a neighborhood of data consisting of the first feature value and the second feature value related to the target image, in a feature space including the second feature value and the first feature value.

### Claim 4 (depends on 1)

The learning apparatus according to claim 1, wherein
the determination unit extracts a second feature value from the target image, by using the learning model, and
the explanation output unit compresses a dimension of a feature value vector that is the second feature value, and calculates a degree of contribution of the second feature value as the degree of contribution of the target image.

### Claim 5 (depends on 4)

The learning apparatus according to claim 4, wherein the explanation output unit compresses the feature value vector into one dimension.

### Claim 6 (depends on 1)

The learning apparatus according to claim 1, further comprising a feature calculation unit which calculates at least one of first feature values, each of which is the first feature value, for inputting to the learning model, based on the target image.

### Claim 7 (depends on 1)

The learning apparatus according to claim 1, wherein the learning model includes a convolutional neural network.

### Claim 8 (depends on 1)

The learning apparatus according to claim 1, wherein the explanation output unit further outputs an image showing a basis for the determination in the target image, for the result of the determination by the learning model.

### Claim 9 (depends on 1)

The learning apparatus according to claim 1, wherein the explanation output unit causes the degree of contribution of the target image and the degree of contribution of the first feature value, to be aligned and displayed.

### Claim 10 (depends on 8)

The learning apparatus according to claim 8, wherein the explanation output unit causes the degree of contribution of the target image, the degree of contribution of the first feature value, the image showing the basis for the determination, and the result of the determination, to be aligned and displayed.

### Claim 11 (depends on 9)

The learning apparatus according to claim 9, wherein the explanation output unit causes text which corresponds to each of the degree of contribution of the target image and the degree of contribution of the first feature value, to be displayed.

### Claim 12

A non-transitory computer-readable medium having recorded thereon a program which causes a computer to implement:
a storing function of storing, in a storage unit, a learning model that is trained by setting, as an input, a training image set and a training feature value set that is related to a subject of the training image set and that is obtained by quantifying a predetermined interpretable feature, and by setting, as an output, results of a determination on the training image set and the training feature value set;
a determining function of outputting, by using the learning model stored in the storage unit, results of a determination on a target image and a first feature value that is related to a subject of the target image and that is obtained by quantifying the predetermined interpretable feature; and
an explanation outputting function of outputting a degree of contribution of the target image and a degree of contribution of the first feature value, for the result of the determination on the target image and the first feature value by the learning model.

### Claim 13

A learning apparatus which uses a learning model that is trained by setting, as an input, a training image set and a training feature value set that is related to a subject of the training image set and that is obtained by quantifying a predetermined interpretable feature, and by setting, as an output, results of a determination on the training image set and the training feature value set, and which outputs results of a determination on a target image and a first feature value that is related to a subject of the target image and that is obtained by quantifying the predetermined interpretable feature, the learning apparatus comprising:
an explanation output unit which outputs a degree of contribution of the target image and a degree of contribution of the first feature value, for the result of the determination on the target image and the first feature value by the learning model.
