OEM Product Identification via Feature Point Neighborhood Graphs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing methods for identifying Original Equipment Manufacturer (OEM) products are inefficient, often relying on manual inspection and failing to accurately distinguish between similar products due to differing brand logos, leading to potential vulnerabilities going unaddressed.

Innovation Solution

An identification apparatus that processes images by extracting feature points, removing logos, and comparing neighborhood graphs to determine similarity between images, allowing for efficient identification of OEM products.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspection of product labels is used to identify OEM products, then identification accuracy can be maintained, but productivity is significantly reduced and the process becomes time-consuming

Engineering Contradiction:

Improveidentification accuracyVSAvoididentification efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual mechanical inspection with an automated image processing system that captures product images, extracts feature points, and compares neighborhood graphs to identify OEM products. This substitution of mechanical/manual processes with automated computational methods resolves the contradiction by achieving both high identification accuracy and improved productivity through automation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If brand logos are used as the primary identification feature, then ease of operation is improved, but reliability deteriorates because different brands may have similar product designs

Engineering Contradiction:

Improveidentification simplicityVSAvoididentification reliability

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent extracts and removes brand logo information from the image analysis process by focusing on neighborhood graphs of feature points that represent the underlying product structure. This extraction of essential structural features while eliminating brand-specific identifiers allows the system to identify OEM relationships based on design similarities rather than brand labels, improving reliability without sacrificing operational ease.

Inventive Principle:

Principle #2Taking out (Extraction)

3Productivity

If automated image processing is implemented to improve productivity, then identification efficiency increases, but device complexity increases due to the need for advanced image processing algorithms

Engineering Contradiction:

Improveidentification efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the image processing task into distinct modules: feature point extraction, neighborhood graph generation, and graph comparison. This segmentation of the automated processing system into manageable functional components achieves high identification efficiency while controlling complexity through modular design, allowing each component to be optimized independently.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11830238B2Identification device, identification method, and identification program

Publication Date: 2023.11.28 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

An identification apparatus includes processing circuitry configured to determine whether or not a first image and a second image are similar based on feature points extracted from each of the first image and the second image, and determine whether or not the first image and the second image are similar by comparing neighborhood graphs generated for each of the first image and the second image, the feature points being as nodes.