Individual Identification Device Using Partial Area Effectiveness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of individual identification is compromised when there are image components common to multiple registered images, as existing methods struggle to effectively account for patterns unique to manufacturing apparatuses, leading to decreased collation accuracy.
Innovation Solution
An individual identification device and method that decide the effectiveness of image components for similarity scoring by determining if partial areas contain common image components across multiple registered images, using Fourier-Mellin feature extraction and partial area analysis to isolate unique features, thereby adjusting scoring to exclude common patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all image components are used for similarity scoring, then the completeness of image comparison is improved, but the accuracy of individual identification deteriorates due to common image components from manufacturing apparatuses
Solution Approach 1:
The patent segments the image into multiple partial areas and evaluates each area's effectiveness individually. By dividing the image into regions and assessing their contribution to identification accuracy, the system can selectively use only those partial areas that provide unique individual characteristics, excluding regions dominated by common manufacturing patterns.
Solution Approach 2:
The patent applies local quality by assigning different effectiveness values to different partial areas of the image. Areas containing unique individual features are given higher effectiveness weights, while areas dominated by common manufacturing apparatus patterns are given lower or zero effectiveness, thereby optimizing the overall identification accuracy.
2Reliability
If Fourier-Mellin transformation is used for feature extraction, then the robustness to geometric transformations is improved, but the computational complexity increases
Solution Approach 1:
The patent applies partial action by performing Fourier-Mellin transformation only on selected partial areas that have been identified as effective for individual identification. Rather than transforming the entire image, the system processes only those regions that contribute meaningfully to accuracy, reducing computational burden while maintaining robustness where needed.
Data Source
AI summary
When there is an image component common to multiple registered images, the accuracy of individual identification lowers. A decision unit decides, for each partial area, the degree of effectiveness relating to calculation of a score representing a similarity between a registered image obtained by capturing an object to be registered and a collated image obtained by capturing an object to be collated, based on whether or not the partial area contains an image component common to multiple registered images obtained by capturing multiple objects to be registered. A calculation unit calculates the score based on image components contained in the registered image and the collated image and on the degrees of effectiveness.