Synthesized Iris Code Generation for Authentication Memory Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current iris authentication methods face challenges in enhancing recognition performance and memory efficiency due to variations in image quality and the influence of blocks with low correlations, leading to decreased authentication rates and increased memory usage.
Innovation Solution
The method generates a synthesized iris code and mask code based on correlations between iris codes in block units, determining the greatest and second greatest correlations to create a representative code for each block position, which is then used to update the enroll set and authenticate images, thereby improving recognition performance and reducing memory usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If iris codes are stored in the enroll set for authentication, then authentication capability is provided, but memory usage increases
Solution Approach 1:
Multiple iris codes from different image positions are merged into a single synthesized iris code by selecting blocks with greatest correlations. This combines the authentication capability of multiple codes into one representative code, maintaining reliability while reducing the quantity of stored data.
Solution Approach 2:
Instead of storing all original iris codes, the system creates a synthesized copy that represents the essential authentication information. This synthesized code serves as a representative substitute for multiple original codes, reducing memory requirements while preserving authentication functionality.
2Measurement precision
If all iris codes in the enroll set are used for authentication, then authentication accuracy is maintained, but processing time increases due to redundant calculations
Solution Approach 1:
The system extracts only the most relevant information from multiple iris codes by identifying blocks with greatest correlations and synthesizing a representative code. This extraction process removes redundant data while preserving the essential authentication features, reducing processing time without sacrificing accuracy.
Solution Approach 2:
The synthesized code is pre-generated during enrollment by analyzing correlations among all iris codes. This preliminary synthesis prepares a representative authentication template in advance, so that during actual authentication, the system only needs to compare against the pre-synthesized code rather than processing multiple original codes, significantly reducing authentication time.
3Adaptability or versatility
If iris codes with low correlations are included in authentication, then comprehensive coverage is achieved, but recognition performance decreases
Solution Approach 1:
The system applies different quality standards to different blocks of iris codes by evaluating correlations and selectively including only high-correlation blocks in the synthesized code. This local quality approach ensures that only reliable, high-correlation regions contribute to authentication, improving recognition performance while maintaining comprehensive coverage of important iris features.
Data Source
AI summary
An authentication method and corresponding apparatus includes obtaining iris images, and constituting an enroll set including iris codes and mask codes corresponding to the iris images. The authentication method and corresponding apparatus also include generating a synthesized code including a synthesized iris code and a synthesized mask code based on correlations between the iris codes included in the enroll set in block units.