# US 2026/0073506 A1 · Article inspection device

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

- Number: US 2026/0073506 A1
- Document ID: US20260073506A1
- Status: Published application
- Kind: A1
- Application number: 19/316,230
- Filed: 2025-09-02
- Published: 2026-03-12
- Earliest claimed: 2024-09-10
- Assignees: Anritsu Corporation
- Applicants: Anritsu Corporation
- Inventors: Takeshi YAMAZAKI; Koetsu TSUNODA
- Web page: https://patentgrep.com/patent/US20260073506A1

## CPC

- G06T 7/001: {using an image reference approach}
- G06T 7/0004: {Industrial image inspection}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 10/776: Validation; Performance evaluation
- G06T 2207/10116: X-ray image
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30128: Food products
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An article inspection device capable of increasing accuracy of learning or performance verification without an effort to acquire an inspection image to be used for learning or performance verification for setting an inspection condition is provided. An article inspection device includes an inspection unit that inspects a quality state of an article using an inspection image obtained by imaging the article being transported, in which the inspection unit sets an inspection condition of the quality state of the article based on a pseudo-image of the inspection image generated by a generative AI. The inspection unit inspects the quality state of the article by applying a trained model as an inspection condition created by learning the pseudo-image.

## Claims

### Claim 1

An article inspection device comprising:
an inspection unit that inspects a quality state of an article (P) using an inspection image (Dpx) obtained by imaging the article being transported,
wherein the inspection unit sets an inspection condition of the quality state of the article based on a pseudo-image (Dpp) of the inspection image generated by a generative AI.

### Claim 2 (depends on 1)

The article inspection device according to claim 1,
wherein the inspection unit sets the inspection condition using a trained model created by learning the pseudo-image.

### Claim 3 (depends on 1)

The article inspection device according to claim 1, further comprising:
an image processing algorithm storage unit that stores a plurality of image processing algorithms in advance; and
an evaluation unit that evaluates appropriateness of inspection of the quality state using the pseudo-image of the inspection image and calculates a plurality of evaluation values for each of the plurality of image processing algorithms,
wherein the inspection unit inspects the quality state of the article by applying an image processing algorithm (Pgm) selected based on the plurality of evaluation values.

### Claim 4 (depends on 2)

The article inspection device according to claim 2, further comprising:
an image processing algorithm storage unit that stores a plurality of image processing algorithms in advance; and
an evaluation unit that evaluates appropriateness of inspection of the quality state using the pseudo-image of the inspection image and calculates a plurality of evaluation values for each of the plurality of image processing algorithms,
wherein the inspection unit inspects the quality state of the article by applying an image processing algorithm (Pgm) selected based on the plurality of evaluation values.

### Claim 5 (depends on 2)

The article inspection device according to claim 2,
wherein a dataset to be used for training the trained model includes a dataset obtained by creating pseudo-images (Dpp1) based on normal product sample images (Dps1) and automatically adding an OK tag to the pseudo-images.

### Claim 6 (depends on 2)

The article inspection device according to claim 2,
wherein a dataset to be used for training the trained model includes a dataset obtained by creating pseudo-images (Dpp2) based on defective product sample images (Dps2) and automatically adding a defective product tag to the pseudo-images and a dataset obtained by creating pseudo-images (Dpp3) based on defective part sample images (Dps3) and automatically adding a foreign object label to the pseudo-images.

### Claim 7 (depends on 3)

The article inspection device according to claim 3,
wherein the evaluation unit evaluates whether or not normal product determination is executable with a probability greater than or equal to a predetermined correct answer rate and whether: or not defective product determination is executable with a probability greater than or equal to a predetermined correct answer rate.
