# US 2026/0017814 A1 · Learning Model-Based Dimension Measurement Device and Method

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

- Number: US 2026/0017814 A1
- Document ID: US20260017814A1
- Status: Published application
- Kind: A1
- Application number: 18/858,976
- Filed: 2023-08-30
- Published: 2026-01-15
- Earliest claimed: 2022-08-31
- Assignees: LG Energy Solution, Ltd.
- Applicants: LG Energy Solution, Ltd.
- Inventors: Jaejin Kim; Tae Young Kim
- Web page: https://patentgrep.com/patent/US20260017814A1

## CPC

- G06N 3/08: Learning methods
- G06T 7/62: of area, perimeter, diameter or volume
- G01B 11/022: {by means of tv-camera scanning}
- G06N 3/045: Combinations of networks
- G06N 3/09: Supervised learning
- G06T 7/12: Edge-based segmentation
- G06V 20/70: Labelling scene content, e.g. deriving syntactic or semantic representations
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The size measuring apparatus and method according to embodiments of the present invention can obtain highly reliable dimension measurement result data with improved precision by obtaining dimension information of a specific object in an image of interest using a pre-trained learning model.

## Claims

### Claim 1

An apparatus of learning model-based size measurement, the apparatus comprising:
at least one processor; and
a memory configured to store at least one instruction executed by the at least one processor,
wherein the at least one instruction includes:
an instruction to acquire an image of interest from an object image, the object image containing a measurement object of which size is to be measured, and
an instruction to input the image of interest into a pre-trained learning model and to output result data including dimension information of the measurement object.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the pre-trained learning model is a deep learning based learning model.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the instruction to output result data including dimension information of the measurement object includes an instruction to segment the image of interest into at least one physical object using the pre-trained learning model and an instruction to label a size measurement point of the measurement object.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the instruction to acquire the image of interest includes an instruction to obtain the image of interest from the object image using a rule-based algorithm.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the instruction to obtain the image of interest includes an instruction to perform image pre-processing on the object image.

### Claim 6

A method of learning model-based size measurement, the method comprising:
acquiring an image of interest from an object image, the object image containing a measurement object of which size is to be measured; and
inputting the image of interest into a pre-trained learning model and outputting result data including dimension information of the measurement object.

### Claim 7 (depends on 6)

The method of claim 6, wherein the pre-trained learning model is a deep learning based learning model.

### Claim 8 (depends on 6)

The method of claim 6, wherein the outputting result data including dimension information of the measurement object includes segmenting the image of interest into at least one physical object using the pre-trained learning model and labeling a size measurement point of the measurement object.

### Claim 9 (depends on 6)

The method of claim 6, wherein the acquiring the image of interest includes obtaining the image of interest from the object image using a rule-based algorithm.

### Claim 10 (depends on 9)

The method of claim 9, wherein the obtaining the image of interest includes performing image pre-processing on the object image.
