Automated Image Similarity Detection Using Feature Extraction Modules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for identifying similarities between original and copied works, such as copyrighted images or product packaging, are manual and resource-intensive, making it difficult to efficiently distinguish between authentic and copied items in crowded marketplaces.
Innovation Solution
A system and method that utilize a feature extraction module to generate product signatures from candidate and target data sets, which are then compared by a decision module to determine similarity, with optional user validation and explanation tools like heat maps to aid in decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual processes are used to determine similarity between original and potential copies, then measurement precision can be maintained through human expertise, but productivity is severely reduced due to time-consuming analysis
Solution Approach 1:
The patent replaces manual visual inspection and expert analysis with an automated computer-based system that uses image processing algorithms and machine learning models to detect and compare features between original and potential copy images, thereby maintaining measurement precision while dramatically improving productivity
Solution Approach 2:
The system introduces an intermediary automated analysis platform that acts as a mediator between the original image, potential copies, and the final similarity determination, using feature extraction and comparison algorithms to bridge the gap between raw images and similarity assessment
2Measurement precision
If comprehensive feature extraction is performed to ensure accurate similarity detection, then measurement precision improves, but device complexity increases due to multiple processing modules
Solution Approach 1:
The system segments the similarity detection process into distinct functional modules: image pre-processing, feature extraction, feature comparison, and similarity scoring. Each module handles a specific aspect of the analysis, allowing comprehensive feature extraction while managing complexity through modular architecture
Solution Approach 2:
The patent implements a universal feature extraction framework that can handle multiple types of features (geometric, textural, color, semantic) using the same underlying system architecture, reducing device complexity by avoiding separate specialized systems for each feature type
3Productivity
If automated similarity detection is implemented to improve productivity, then analysis speed increases, but measurement precision may deteriorate due to algorithmic limitations
Solution Approach 1:
The system incorporates feedback mechanisms where similarity assessment results are continuously refined based on comparison outcomes, allowing the algorithm to adjust its detection thresholds and parameters to maintain high measurement precision while processing large volumes of images efficiently
Solution Approach 2:
The patent performs preliminary actions by pre-processing images and extracting key features before the main similarity comparison, preparing the data in advance to enable both high-speed automated processing and accurate measurement without sacrificing precision
Data Source
AI summary
Systems and methods for determining similarities between an input data set and a target data set with the data sets being vector representations of the features of a candidate potential copy and a target original. A feature extraction module receives an image of the potential copy and extracts the features of that candidate. The features of the target original may already be extracted or may be separately extracted. The resulting data sets for the candidate and the original are then passed through a decision module. The decision module determines a level of similarity between the features of the candidate and the features of the original. The output of the decision module provides an indication of this level of similarity and, depending on this level of similarity, an alert may be generated. A report module may be included to provide an explanation regarding the level of similarity.