# US 12,217,495 B2 · Learning process device and inspection device

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

- Number: US 12,217,495 B2
- Document ID: US12217495B2
- Status: Granted
- Kind: B2
- Application number: 17/642,423
- Filed: 2020-09-16
- Published: 2022-10-27
- Granted: 2025-02-04
- Earliest claimed: 2019-09-17
- Assignees: Syntegon Technology GmbH
- Applicants: Syntegon Technology K.K.
- Inventors: Ken Wada
- Web page: https://patentgrep.com/patent/US12217495B2

## CPC

- G06V 10/82: using neural networks
- G06T 7/0004: {Industrial image inspection}
- G06V 10/7747: {Organisation of the process, e.g. bagging or boosting}
- G06V 10/776: Validation; Performance evaluation
- G01N 21/90: in a container or its contents (G01N21/91 takes precedence)
- G01N 2021/8883: {involving the calculation of gauges, generating models}
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30108: Industrial image inspection
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)

## Abstract

A learning processing device that is based on a neural network model and image data obtained by capturing an image of the object to be inspected, and constructs the neural network model used for inspecting the object to be inspected. The learning processing device is provided with a learning unit which performs a learning process under a prescribed learning condition on the basis of a list of the image data including a plurality of learning images and constructs the neutral network model. The learning unit embeds unique model identification data in the neural network model, whenever the neural network model is constructed.

## Claims

### Claim 1

A learning processing apparatus for constructing a neural network model for use in inspection of an inspection target based on image data obtained by capturing an image of the inspection target and the neural network model,
the learning processing apparatus comprising:
a learning unit configured to execute learning processing under predetermined learning conditions based on a list of image data including a plurality of learning images to construct a neural network model,
wherein the learning unit is configured to assign, when the list of image data or the learning conditions is at least partially changed, unique model identification data to a combination of the list of image data and the learning conditions in which the list of image data or learning conditions is changed and embed the unique model identification data with respect to a neural network model constructed with the list of image data and the learning conditions, thereby embedding unique model identification data in the neural network model, each time the learning unit constructs the neural network model.

### Claim 2 (depends on 1)

The learning processing apparatus according to claim 1, wherein the model identification data is binary data.

### Claim 3

An inspection apparatus for inspecting an inspection target according to a data file of preset inspection processing conditions, the inspection apparatus comprising:
a learning unit configured to execute learning processing under predetermined learning conditions based on a list of image data including a plurality of learning images to construct a neural network model,
a processing condition setting unit configured to generate the data file of inspection processing conditions to which the constructed neural network model is applied; and
an inspection unit configured to determine a defect of the inspection target based on image data obtained by capturing an image of the inspection target and the neural network model, according to the data file of inspection processing conditions, wherein
the learning unit is configured to assign, when the list of image data or the learning conditions is at least partially changed, unique model identification data to a combination of the list of image data and the learning conditions in which the list of image data or the learning conditions is changed and embed the unique model identification data with respect to a neural network model constructed with the list of image data and the learning conditions to thereby embed unique model identification data in the neural network model each time the learning unit constructs the neural network model, thereby constructing the neural network model with unique model identification data assigned thereto, each time the learning unit constructs the neural network model, and
the processing condition setting unit is configured to generate the inspection processing conditions with unique condition identification data assigned thereto, each time a neural network model to be applied is changed.

### Claim 4 (depends on 3)

The inspection apparatus according to claim 3, wherein the condition identification data is binary data.