Individual Identifying Device for Multi-Object Discrimination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in determining an imaging condition suitable for identifying three or more objects that are similar to one another, as they are primarily designed for distinguishing between two similar objects, making it difficult to effectively read and differentiate unique fine uneven patterns on the surfaces of mass-produced items.
Innovation Solution
An individual identifying device that captures multiple images of each object under varying imaging conditions, extracts feature amounts, generates feature amount pairs for same and different types of objects, and determines the appropriateness of imaging parameters based on the separation between distributions of collation scores to identify optimal imaging conditions for distinguishing between multiple similar objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If imaging conditions are optimized for distinguishing two similar objects, then discrimination accuracy between two objects is improved, but the capability to identify three or more similar objects deteriorates
Solution Approach 1:
The patent applies parameter changes by systematically varying imaging parameters (illumination angle, polarization angle, wavelength) to capture images under multiple different conditions. This allows the system to extract feature amounts that are robust across different object types, enabling identification of three or more similar objects rather than just two. The feature amount extraction process uses these varied parameters to create discrimination criteria that generalize across multiple object classes.
2Adaptability or versatility
If multiple imaging parameters are varied to identify three or more objects, then identification capability is improved, but device complexity and measurement difficulty increase
Solution Approach 1:
The patent applies segmentation by dividing the imaging process into distinct stages: first varying illumination angles to capture geometric features, then varying polarization angles to capture material properties, and finally varying wavelengths to capture spectral characteristics. This segmented approach to parameter variation allows systematic exploration of the parameter space while maintaining manageable device complexity, as each parameter can be controlled independently.
Solution Approach 2:
The patent implements multi-functionality by using a single imaging system that can operate under multiple imaging conditions by adjusting illumination and detection parameters. The same imaging device captures images under different illumination angles, polarization states, and wavelengths, eliminating the need for multiple specialized devices and reducing overall system complexity while maintaining high identification capability.
3Measurement precision
If feature amounts are extracted under multiple imaging conditions, then discrimination accuracy is improved, but processing time and loss of time increase
Solution Approach 1:
The patent applies preliminary action by pre-determining the optimal set of imaging parameters to vary based on the specific application requirements. Rather than exhaustively searching all possible parameter combinations, the system预先 selects the most informative parameters (illumination angle, polarization angle, wavelength) and their specific values, which reduces processing time while maintaining high discrimination accuracy for identifying three or more similar objects.
Data Source
AI summary
An imaging unit, an extraction unit, a feature amount pair generation unit, and an imaging parameter adjustment unit are included. The imaging unit acquires images obtained by imaging each of N (N≥3) types of objects a plurality of times by setting a value of a specific imaging parameter, among a plurality of types of imaging parameters, as a certain candidate value and changing a value of the remaining imaging parameter. The extraction unit extracts a feature amount from each of the images. The feature amount pair generation unit generates, as a first feature amount pair for each of the N types of objects, a feature amount pair in which two feature amounts constituting the feature amount pair are extracted from images of objects of the same type, and generates, as a second feature amount pair for every combination of the N types of objects, a feature amount pair in which two feature amounts constituting the feature amount pair are extracted from a images of objects of the different types. The imaging parameter adjustment unit generates a first distribution that is a distribution of collation scores of the first feature amount pairs, generates a second distribution that is a distribution of collation scores of the second feature amount pairs, and on the basis of a degree of separation between the first distribution and the second distribution, determines the propriety of adopting the candidate value.