Seal Authenticity Verification Using ML Edge Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack the ability to distinguish between original and duplicate plastic seals, as they cannot detect minor printing differences caused by variations in printing technology, substrate material, and surface finish, allowing counterfeiters to create convincing duplicates.
Innovation Solution
A system and method utilizing machine learning and computer vision to generate unique fingerprints of seals by breaking down images into sub-images, applying edge detection rules, and comparing these fingerprints to a pre-trained model to determine authenticity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional printing technologies are used to create seal duplicates, then the visual appearance can be replicated, but the printing precision and minor details cannot be reproduced due to technology limitations
Solution Approach 1:
The seal image is divided into multiple sub-images by forming a grid pattern, allowing detailed analysis of specific regions. This segmentation enables the system to capture and compare minor printing differences that would be imperceptible in the overall image, thereby resolving the contradiction between visual replication and printing precision.
Solution Approach 2:
The system applies edge detection rules to specific sub-images rather than the entire seal image, focusing computational resources on regions with critical printing details. This local quality approach allows the system to identify subtle printing variations in specific areas while maintaining overall system efficiency, addressing the manufacturing precision limitation.
2Measurement precision
If a simple visual inspection method is used, then the system is easy to operate, but it cannot detect minor printing differences between original and duplicate seals
Solution Approach 1:
The patent replaces manual visual inspection with an automated computer vision system that uses machine learning models and edge detection algorithms. This substitution transforms the authentication process from a subjective human task to an objective computational process, significantly improving measurement precision while managing device complexity through automated processing.
Solution Approach 2:
The system creates a digital fingerprint copy of the seal's edge structures and compares it against stored reference fingerprints. This copying approach allows for precise digital analysis of printing differences without requiring complex physical measurement devices, balancing authentication accuracy with system complexity.
3Measurement precision
If the entire seal image is analyzed at once, then the processing is simple, but minor printing differences are lost due to lack of detail resolution
Solution Approach 1:
The seal image is divided into multiple sub-images by forming a grid pattern, allowing detailed analysis of specific regions. This segmentation enables the system to capture and compare minor printing differences that would be imperceptible in the overall image, thereby resolving the contradiction between visual replication and printing precision.
Solution Approach 2:
The system transforms the 2D seal image into a multi-dimensional analysis structure by creating sub-images and extracting edge features. This dimensional transformation allows the system to analyze printing details at multiple levels of resolution, improving detail detection capability while managing processing complexity through structured analysis.
Data Source
AI summary
In one aspect, a computerized method for anti-counterfeiting solution using a machine learning (ML) model includes the step of providing a pre-defined set of feature detection rules, a pre-defined set of edge detection rules, a pre-defined threshold percentage, an original seal, an original fingerprint of the original seal, and a pre-trained fingerprint identification model. The pre-trained fingerprint identification model is trained by a specified ML algorithm using one or more digital images of the original seal. With a digital camera of a scanning device, the method scans a seal whose authenticity is to be determined. The seal is used to secure a transportation container. The method uses the pre-defined set of feature detection rules to detect and extract an extracted feature image at a specified position on the seal. The method breaks down the extracted feature image of the seal into a ‘kn’ number of sub-images by forming a ‘k’ rows x ‘n’ columns of a grid of the extracted feature image. The method implements the pre-defined set of edge detection rules to extract an edge structure of at least one object in each of the ‘kn’ number of sub-images. The method generates a set of unique fingerprints by specified steps. The method includes generating a unique fingerprint corresponding to a unique number or a feature based on each extracted edge structure. For the set of unique fingerprints, the method generates a match percentage for the set of unique fingerprints using the pre-trained fingerprint identification model. The match percentage corresponds to a matching proportion between each unique fingerprint generated for the seal being verified and the original fingerprint of the original seal on which the pre-trained fingerprint identification model is trained.