Image Novelty Detection for Material Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for authenticating materials or products suspected of being counterfeit are time-consuming and inefficient, often requiring shipment to technical experts for laboratory testing.
Innovation Solution
A computer-implemented method and system that uses a trained transformation function to process images of test samples against a batch of authentic material samples, determining novelty based on similarity measures, allowing for proactive identification of counterfeits without requiring data from counterfeit samples.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional laboratory testing methods are used to authenticate materials, then measurement precision can be maintained, but loss of time increases significantly
Solution Approach 1:
The patent replaces physical laboratory testing mechanisms with a computational image processing system. A trained transformation function processes images of material samples to extract features and determine authenticity, substituting mechanical/chemical lab tests with automated computer vision analysis that delivers rapid results without sacrificing authentication accuracy
Solution Approach 2:
The system performs preliminary training with authentic material images to establish a reference model before actual authentication. This preliminary action creates a transformed matrix representation of genuine materials, enabling rapid comparison and decision-making during subsequent authentication operations without requiring time-consuming lab analysis
2Reliability
If proactive identification without counterfeit data is implemented, then reliability of authentication is improved, but loss of information may increase
Solution Approach 1:
The system extracts essential features from images of authentic materials through the trained transformation function, isolating the key characteristics that define genuine materials. By extracting only the necessary feature representations into a transformed matrix, the system maintains discrimination capability while eliminating the need for counterfeit sample data
Solution Approach 2:
The transformation function creates a computational copy or representation of authentic material characteristics in the form of a transformed matrix. This copy captures the essential patterns and features of genuine materials, enabling reliable authentication through comparison without requiring access to actual counterfeit samples for training
Data Source
AI summary
Systems and methods for detecting/identifying novel material samples are provided. A test sample image is processed with a trained transformation function to obtain a transformed matrix. A measure of similarity of the test image based on the transformed matrix is compared to a threshold to determine whether the test sample is novel to a batch of material samples that are provided to train the transformation function.