Feature Correction for Verification Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing verification systems face challenges in accurately identifying similar data to query data from a large set of registration data, particularly due to factors like varying imaging conditions, occlusions, and similar features among individuals.
Innovation Solution
A verification apparatus and method that includes a verification unit to extract similar data based on a query feature quantity, and a correction unit to adjust this feature quantity using an arithmetic value derived from registration feature quantities of similar data, thereby improving the accuracy of subsequent data extraction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the verification unit extracts similar data based on query feature quantity without correction, then the extraction process is simple and fast, but the verification accuracy is insufficient due to common features among similar data
Solution Approach 1:
The correction unit performs preliminary correction on the query feature quantity before the verification unit uses it for extraction. By pre-adjusting the feature quantity to reduce common features among similar data, the system improves verification accuracy without adding complex processing during the extraction phase itself.
Solution Approach 2:
The correction unit acts as an intermediary between the initial feature extraction and the final verification process. It transforms the raw query feature quantity into a corrected version that better distinguishes target data from similar data, thereby improving accuracy without requiring the verification unit itself to become more complex.
2Reliability
If the system processes all registration data to ensure comprehensive verification, then the verification coverage is complete, but the processing time increases
Solution Approach 1:
The correction unit changes the parameters of the query feature quantity by reducing the weight or influence of common features that appear frequently among similar data. This parameter transformation allows the system to maintain comprehensive verification coverage while improving the efficiency of identifying truly relevant data among the similarities.
Data Source
AI summary
A verification apparatus includes: a verification unit that extracts a plurality of pieces of first similar data similar to query data, from a plurality of pieces of registration data, on the basis of a query feature quantity that is a feature quantity of the query data; and a correction unit that corrects the query feature quantity on the basis of an arithmetic value of a plurality of registration feature quantities that are feature quantities of the plurality of pieces of first similar data, wherein the verification unit extracts at least one piece of second similar data similar to the query data, from the plurality of pieces of registration data, on the basis of the query feature quantity corrected by the correction unit.