Irregular Particle Layer Feature Extraction for Universal Object Identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing individual identification technologies are limited in their application to objects of varying sizes and shapes, as they require specific positioning and range definitions for feature quantity extraction, making them unsuitable for use across multiple kinds of objects.

Innovation Solution

An individual identifier extraction device and method that acquires and extracts a feature quantity based on the planar shape and distribution of fine particles in a layer with an irregular shape, allowing for identification across objects of different sizes and shapes without the need for specific positioning or range definitions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a position and range for extracting feature quantity are defined for each object, then the feature quantity can be extracted accurately, but the application is limited to objects having the same outline and size

Engineering Contradiction:
Improvefeature quantity extraction accuracyVSAvoidapplicability to multiple kinds of objects
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent applies universality by creating a single identification system that works across multiple kinds of objects with different outlines and sizes. The layer containing fine granules serves as a universal identifier that can be applied to any object, and the image processing extracts feature quantities that are invariant to object variations, enabling one system to handle diverse objects effectively

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent changes the parameters used for identification from object-specific parameters (position and range definitions that vary with each object's outline and size) to layer-specific parameters (distribution patterns of fine granules within the layer). This parameter transformation allows the same extraction methodology to be applied universally regardless of the underlying object's characteristics

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If the definition of position and range varies with change of outline and size of object, then the identification can be accurate for each object type, but it becomes difficult to generally apply to multiple kinds of objects

Engineering Contradiction:
Improveidentification accuracyVSAvoidcomplexity of positioning and range definition
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the identification information from the object itself by applying a layer containing fine granules directly onto the object surface. This separates the identifier (the layer with granules) from the object's physical characteristics (outline and size), allowing the identifier to be extracted and processed independently without needing to account for object variations

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent creates a standardized copy of the identifier in the form of a layer with fine granules that can be applied uniformly across different objects. This layer serves as a portable, object-agnostic representation of identification information that can be imaged and processed using the same methodology regardless of the source object's characteristics

Inventive Principle:
Principle #26Copying

Data Source

PatentUS10621429B2Individual identifier extraction device
Publication Date: 2020.04.14 NEC CORP
  • US10621429B2 patent drawing
  • US10621429B2 patent drawing
  • US10621429B2 patent drawing

AI summary

An individual identifier extraction device has: an acquisition part configured to acquire an image of a layer formed on an object, containing fine particles, and having an irregular planar shape; and an extraction part configured to extract a feature quantity dependent on the planar shape of the layer and the distribution of the particles as an individual identifier of the object from the image.